Categories
Uncategorized

Course review: How to use AI and LLMs for Offensive and Defensive Security 

The online course How to use AI and LLMs for Offensive and Defensive Security from 2015 makes a short introduction to relevant topics regarding Artificial Intelligence (AI) and Large Language Models (LLMs) and their usage in the field of cyber security. These topics include theory about LLMs like prompt engineering or tokens. Then it goes on to explain different tools that can be used locally or with remote services such as ChatGPT. After the introduction, the course goes on to show several use cases for offensive security as well as for defensive security.

Although the course is short with only 4.5 hours of video material, it gives a solid and quick overview of the topics mentioned. For example, to myself the section about installing and using LLMs locally is extremely useful, I currently use LM Studio with several different models and will probably also try other tools mentioned in the course, as well as LLMs that could also be used for creating images and short videos.

However, there is one downside to the course; the last update was in April 2025, and for the quick development in the field of AI that is already a very long time. This means that some of the topics discussed in the course might already be outdated. But in conclusion I found the course helpful, because it is very hands-on.

In the meanwhile I setup an AI machine to run LLMs locally with eight GPUs. Next blog post to come.

Categories
Uncategorized

Sicherheit, Digitales & Darüber Hinaus / Security, Digital & Beyond, #58


This is an email newsletter, if you are interested send me a message.


Einen schönen guten Tag,

und willkommen bei Sicherheit, Digitales & Darüber Hinaus, ein Newsletter mit den Themen aus der Cyber Sicherheit, Sicherheitspolitik. Da ich viel lese, Online Kurse mache, Podcasts höre usw., führe ich seit langer Zeit Lese- und Merklisten. Inhalte, die mir weiterhelfen und von denen ich denke, dass sie für andere Menschen ebenfalls interessant sind, teile ich gerne. Um Cyber-Risiken und -Bedrohungen zu verstehen, ist es wichtig, die verschiedenen Bereiche zu kennen, die sich gegenseitig beeinflussen. Dazu gehören Sicherheitspolitik, Geopolitik, Wirtschaft, Desinformation, Spionage, hybride Bedrohungen und technische Themen wie Schwachstellen, Netzwerke, Software, künstliche Intelligenz und mehr.

Der Newsletter ist zweisprachig. Wo es möglich ist, versuche ich Artikel über ein Thema auf Deutsch und Englisch zu finden, und entsprechend zu kennzeichnen.


[EN] Have a nice day,

and welcome to Security, Digital & Beyond, a newsletter with the topics from cyber security, security policy and more. Since I read a lot, do online courses, listen to podcasts, etc., I have been keeping reading and watch lists for a long time. I like to share content that helps me and that I think is interesting for other people as well.

For understanding cyber risks and threats, it is important to understand the different domains influencing each other. This includes  security policy, geo politics, economy, disinformation, espionage, hybrid threats and technical topics such as vulnerabilities, networking, software, artificial intelligence and more. The newsletter is bilingual. Where possible, I try to find articles about a topic in German and English and mark them accordingly.


Cyber

[DE] Staaten wollen weiter hacken, aber mit Regeln

23 Staaten haben sich im Rahmen des „Pall-Mall“-Prozesses auf eine unverbindliche Vorschlagsliste geeinigt, um die Verbreitung von Schadsoftware wie Staatstrojanern und anderen Hacking-Werkzeugen einzudämmen. Experten bewerten die Ideenliste zwar positiv. Praktische Auswirkungen wird die Verabschiedung der Regeln aber nicht entfalten.

https://netzpolitik.org/2025/pall-mall-prozess-staaten-wollen-weiter-hacken-aber-mit-regeln/

[EN] The Pall Mall Process: tackling the proliferation and irresponsible use of commercial cyber intrusion capabilities

We, as participant representatives of States, international organisations, private industry, academia, and civil society met to participate in an international conference hosted by the United Kingdom and France. The conference discussed the challenges posed by the proliferation and irresponsible use of commercial cyber intrusion capabilities and initiated the Pall Mall Process.

https://www.gov.uk/government/publications/the-pall-mall-process-declaration-tackling-proliferation-and-irresponsible-use-of-commercial-cyber-intrusion-capabilities/the-pall-mall-process-tackling-the-proliferation-and-irresponsible-use-of-commercial-cyber-intrusion-capabilities

[EN] Krebs throws himself on the grenade, resigns from SentinelOne after Trump revokes clearances

Illegitimi non carborundum? Nice password, Mr Ex-CISA

https://www.theregister.com/2025/04/17/krebs_quits_sentinelone/

[EN] EU capabilities in space: Scenarios for space security by 2050

Space holds promise for both economic prosperity and the attainment of strategic goals. The EU’s future role in space is contingent on fast-changing geopolitical dynamics, which can range from peaceful cooperation to heightened competition or conflict among global powers. Given the importance of this subject, the European Commission has announced plans to propose an EU space act in the second quarter of 2025. This paper aims to describe the geopolitical context of space activities that affect the EU’s current and future capabilities, with a specific focus on the use of space for security and defence and the response to space-related risks. Four distinct future scenarios present contextual conditions that may shape the EU’s ambitions in space. The scenarios also highlight challenges and opportunities, while considering policy considerations for EU action.

https://www.europarl.europa.eu/thinktank/en/document/EPRS_IDA(2025)765792

[EN] Remote Access Backdoor Discovered in Chinese Robot Dog Unitree Go1

Security researchers have uncovered a pre-installed, undocumented remote access tunnel in Unitree Go1 robot dogs, enabling full remote control and potential lateral network access.

https://cyberinsider.com/remote-access-backdoor-discovered-in-chinese-robot-dog-unitree-go1/


Sonstiges/Others

[DE] Schwarz-Rot schafft Ministerium für Digitalisierung und Staatsmodernisierung

Knapp sechs Wochen nach der Bundestagswahl haben sich CDU, CSU und SPD auf eine Regierungsbildung geeinigt. Ein Digitalministerium kommt, geführt von der CDU.

https://www.heise.de/news/Digitalpolitik-Schwarz-Rot-schafft-Ministerium-fuer-Digitalisierung-10346438.html

[DE] Britische Armee schießt erfolgreich Drohnenschwärme mit Energiewaffe ab

Die britische Armee testet eine Energiewaffe auf Basis von Radiowellen, um Drohnenschwärme zu zerstören. Das System besticht durch geringe Einsatzkosten.

https://www.heise.de/news/Britische-Armee-schiesst-erfolgreich-Drohnenschwaerme-mit-Energiewaffe-ab-10356125.html

[EN] British soldiers take down drone swarm in groundbreaking use of radio wave weapon

British soldiers have successfully tracked, targeted and defeated swarms of drones in the latest trial of a new directed energy weapon developed in the UK.

https://www.gov.uk/government/news/british-soldiers-take-down-drone-swarm-in-groundbreaking-use-of-radio-wave-weapon

[EN] ‘We thought it was the end of the world’: How the US dropped four nuclear bombs on Spain in 1966

In 1966, the remote Spanish village of Palomares found that the “nuclear age had fallen on them from a clear blue sky”. Two years after the terrifying accident, BBC reporter Chris Brasher went to find what happened when the US lost a hydrogen bomb.

https://www.bbc.com/culture/article/20250404-how-the-us-dropped-nuclear-bombs-on-spain-in-1966


Espionage

[DE] Russische Suchanfragen im Netz vor Anschlägen

Vor Bundestags- und Europawahl gab es mehrere Anschläge in Deutschland. Die ZDF-Sendung Terra X History hat nun mögliche Hinweise für russisches Täterwissen im Netz gefunden.

https://www.zdf.de/nachrichten/politik/deutschland/anschlaege-deutschland-russland-hinweise-100.html

[DE] Russische Spionage-Sensoren vor Großbritannien entdeckt

Auf dem Meeresgrund und an der Küste stößt die britische Marine laut Berichten auf russische Spionage-Sensoren. In London glaubt man, dass damit die britischen U-Boote beobachtet werden sollen, die der nuklearen Abschreckung dienen. Ein Militärvertreter spricht von einem “Krieg im Atlantik”.

https://www.n-tv.de/politik/Russische-Spionage-Sensoren-vor-Grossbritannien-entdeckt-article25684682.html

[EN] UK ‘behind the curve’ on Russian undersea spying, former minister says

The comments came after it was revealed the navy had captured Russian sensors suspected of trying to spy on Britain’s nuclear submarines

https://www.independent.co.uk/news/uk/home-news/russian-spying-vanguard-nuclear-submarine-b2728615.html

[EN] Ambassador does not deny Russian attempts to track UK subs

Russia’s ambassador to the UK has not denied allegations that Russian sensors have been hidden in seas around Great Britain in an attempt to track UK nuclear submarines.

https://www.bbc.com/news/articles/c5yl2729nmjo

[EN] The Escalating Global Risk Environment for Submarine Cables

Submarine cables, the information superhighways that underpin the global economy and facilitate worldwide telecommunications, are operating in an increasingly complex and dynamic risk environment. The rapid expansion and evolution of the submarine cable network — fueled by the voracious data demands of mobile users, cloud-based computing, and the business imperatives of hyperscalers such as Amazon, Google, Meta, and Microsoft — must contend with converging geopolitical, physical, and cyber threats.

https://go.recordedfuture.com/hubfs/reports/ta-2023-0627.pdf


Podcast

[DE] #94 Große Leerstellen und kleine Stellschrauben, aka: der Koalitionsvertrag | Klima und Sicherheit

“Sicherheitshalber” ist der Podcast zur sicherheitspolitischen Lage in Deutschland, Europa und der Welt. In Folge 94 diskutieren Thomas Wiegold, Ulrike Franke, Frank Sauer und Carlo Masala die einschlägigen Kapitel im neuen Koalitionsvertrag. Spoiler alert: ein großer Wurf im Lichte der epochalen Herausforderungen ist der Vertrag nicht. Aber ein paar interessante “Nuggets” identifizieren die vier Podcaster dann doch. Insbesondere über die Wehrpflicht und wie es mit ihr – oder auch nicht – weiter gehen kann und müsste, wird debattiert. Im zweiten Teil wendet sich Sicherheitspod die Crew der Klimakrise zu und erörtert, warum man “Sicherheit” nicht denken kann, ohne auch “Klima” zu denken. Abschließend wie immer der “Sicherheitshinweis”, der kurze Fingerzeig auf aktuelle, sicherheitspolitisch einschlägige Themen und Entwicklungen – diesmal mit der Heron, neuen Loitering Munitions, dem Taurus und noch mehr Waffen. Uff.

https://sicherheitspod.de/2025/04/15/94-grosse-leerstellen-und-kleine-stellschrauben-aka-der-koalitionsvertrag-klima-und-sicherheit/

[DE] Kriegstüchtig? Vom strategischen Denken in Deutschland – mit Prof. Sönke Neitzel

Drei Jahre nach Beginn der Zeitenwende hakt es bei der nötigen Umstellung immer noch gewaltig, und zwar nicht nur bei der Bundeswehr selbst. Über Deutschlands strategische Defizite, die Langlebigkeit alter Strukturen, eine wache Bevölkerung und die Aufgaben des wohl kommenden Kanzlers sprechen wir mit dem Militärhistoriker Prof. Dr. Sönke Neitzel von der Universität Potsdam.

https://blubrry.com/ostausschuss_sk/144441420/kriegstchtig-vom-strategischen-denken-in-deutschland-mit-prof-snke-neitzel/


Immer freue ich mich über Anregungen, Vorschläge und eure Meinung.

I am always happy about suggestions, proposals and your opinion.

Bleibt gesund und viele Grüße / Stay healthy and many greetings

Daniel

Categories
Uncategorized

Newsletter: Sicherheit, Digitales & Darüber Hinaus / Security, Digital & Beyond, #40

This is an email newsletter, if you are interested send me a message.

Einen schönen guten Tag,

und willkommen bei Sicherheit, Digitales & Darüber Hinaus, ein Newsletter mit den Themen aus der Cyber Sicherheit, Sicherheitspolitik. Da ich viel lese, Online Kurse mache, Podcasts höre usw., führe ich seit langer Zeit Lese- und Merklisten. Inhalte, die mir weiterhelfen und von denen ich denke, dass sie für andere Menschen ebenfalls interessant sind, teile ich gerne. Um Cyber-Risiken und -Bedrohungen zu verstehen, ist es wichtig, die verschiedenen Bereiche zu kennen, die sich gegenseitig beeinflussen. Dazu gehören Sicherheitspolitik, Geopolitik, Wirtschaft, Desinformation, Spionage, hybride Bedrohungen und technische Themen wie Schwachstellen, Netzwerke, Software, künstliche Intelligenz und mehr.

Der Newsletter ist zweisprachig. Wo es möglich ist, versuche ich Artikel über ein Thema auf Deutsch und Englisch zu finden, und entsprechend zu kennzeichnen.

[EN] Have a nice day, and welcome to Security, Digital & Beyond, a newsletter with the topics from cyber security, security policy and more. Since I read a lot, do online courses, listen to podcasts, etc., I have been keeping reading and watch lists for a long time. I like to share content that helps me and that I think is interesting for other people as well.

For understanding cyber risks and threats, it is important to understand the different domains influencing each other. This includes  security policy, geo politics, economy, disinformation, espionage, hybrid threats and technical topics such as vulnerabilities, networking, software, artificial intelligence and more. The newsletter is bilingual. Where possible, I try to find articles about a topic in German and English and mark them accordingly.

Herzlichen Dank an die vielen interessanten Kontakte und den großartigen Input.

Thank you for the many interesting contacts and the great input.

Cyber

[DE] US-Regierungsbehörden: IT seit Jahren durch chinesische Angreifer unterwandert

Sicherheitsbehörden in den USA schlagen Alarm – Volt Typhoon ist bereits vor Jahren in kritische US-Infrastrukturen eingedrungen. Ursprung der Attacken: China.

https://www.heise.de/news/US-Regierungsbehoerden-IT-seit-Jahren-durch-chinesische-Angreifer-unterwandert-9624187.html

[EN] Face Off: Group-IB identifies first iOS trojan stealing facial recognition data

Group-IB uncovers the first iOS Trojan harvesting facial recognition data used for unauthorized access to bank accounts. The GoldDigger family grows

https://www.group-ib.com/blog/goldfactory-ios-trojan

[DE] Cyberangriff auf PSI Software

PSI Software entwickelt Software für Energie- und Verkehrsbetriebe. Nachdem das Berliner Unternehmen am 15. Februar seine IT-Systeme wegen eines Cyberangriffs komplett vom Internet trennte, hat es jetzt bestätigt, dass es sich dabei um einen Ransomware-Angriff handelt – gibt aber Entwarnung für Kundensysteme.

https://www.channelpartner.de/a/cyberangriff-auf-psi-software,3617658

[DE] Nordkoreas Hacker mit deutschen Zielen

Das Bundesamt für Verfassungsschutz und der südkoreanische Nachrichtendienst warnen vor Attacken durch nordkoreanische Hackergruppen – auch auf die deutsche Rüstungsindustrie.

https://www.zdf.de/nachrichten/digitales/nordkorea-hacker-verfassungsschutz-100.html

[DE] DOKU: Putins Bären – Die gefährlichsten Hacker der Welt

Die Macher von Simplicissimus entmystifzieren die gefährlichsten Hacker der Welt. Sie nennen sich Fancy Bear oder Cozy Bear und sind Eliteeinheiten russischer Geheimdienste. Ihre Ziele: Der Bundestag, die US-Wahlen und aktuell die Ukraine.

https://www.ardmediathek.de/video/putins-baeren/putins-baeren-die-gefaehrlichsten-hacker-der-welt/swr/Y3JpZDovL3N3ci5kZS9hZXgvbzIwMDQ0NjI

[EN] German battery maker Varta halts production after cyberattack

Battery maker VARTA AG announced yesterday that it was targeted by a cyberattack that forced it to shut down IT systems, causing production to stop at its plants.

https://www.bleepingcomputer.com/news/security/german-battery-maker-varta-halts-production-after-cyberattack

Krieg und Spionage / War and Espionage

[EN] INTERNATIONAL SECURITY AND ESTONIA 2024

https://raport.valisluureamet.ee/2024/en

[DE] Abgeordnete befürchten Russland-Spionage durch die AfD

Mehrere Abgeordnete des Bundestags sind alarmiert. Es gibt offenbar Hinweise, dass die russische Botschaft dabei hilft, AfD-Inhalte zu verbreiten. Umgekehrt besteht die Möglichkeit, dass die rechtsextreme Partei geheime Informationen des Parlaments an Moskau weitergibt.

https://www.n-tv.de/politik/Abgeordnete-befuerchten-Russland-Spionage-durch-die-AfD-article24732970.html

[DE] Für den Frieden: KI setzt in Kriegssimulation Atomwaffen ein

US-Forscher haben untersucht, wie sich große Sprachmodelle in der Simulation eines fiktiven politischen Konflikts verhalten. Die Ergebnisse sind beunruhigend.

https://www.heise.de/news/Fuer-den-Frieden-KI-setzt-in-Kriegssimulation-Atomwaffen-ein-9628928.html

[EN] Western leaders point finger at Putin after Alexei Navalny’s death in jail

Russian opposition leader’s death described as political assassination attributable to president

https://www.theguardian.com/world/2024/feb/16/russian-activist-and-putin-critic-alexei-navalny-dies-in-prison?CMP=share_btn_tw

[DE] FBI-Informant soll im Fall Hunter Biden mit Russland kooperiert haben

Ein FBI-Mitarbeiter soll Vorwürfe gegen den Sohn von US-Präsident Joe Biden erfunden haben. Nun gab er zu: Seine Behauptungen stammten vom russischen Geheimdienst.

[DE] Fast 450 Drohnen über Bundeswehrstandorten gesichtet

Über Truppenübungsplätzen der Bundeswehr tauchen nach Informationen von WDR und NDR seit Beginn des Ukraine-Kriegs vermehrt Drohnen auf. Sicherheitsbehörden befürchten, dass Russland die Ausbildung von ukrainischen Soldaten ausspioniert.

https://www.tagesschau.de/investigativ/ndr-wdr/zunahme-drohnensichtungen-100.html

[EN] Incredibly, The Russian Air Force Has Lost Another Rare A-50 Radar Plane

Incredibly, the Russian air force has lost another one of its rare Beriev A-50M/U Mainstay radar early-warning planes. Video that circulated online on Friday reportedly depicts the A-50’s burning wreckage in Krasnodar Krai, in Russia just east of the Sea of Azov.

https://www.forbes.com/sites/davidaxe/2024/02/23/incredibly-the-russian-air-force-has-lost-another-one-of-its-rare-a-50-radar-planes/?sh=e9cd5f02ac49

Munich Security Conference

Video recordings from the Munich Security Conference

https://www.youtube.com/channel/UCIRbGqZ-epWOAk8wWmwDy3A

[DE] Stärkerer Schutz von Wirtschaft und Wissenschaft vor Spionage und Sabotage

Pressemitteilung: Eckpunkte für eine Nationale Wirtschaftsschutzstrategie

https://www.bmi.bund.de/SharedDocs/pressemitteilungen/DE/2024/02/eckpunkte-nws.html?nn=9390260

[DE] Zum Start ein Schock – dann viel Ratlosigkeit

Die 60. Münchner Sicherheitskonferenz ist zu Ende – dominiert von den Themen Ukraine und Nahost. Welche Eindrücke bleiben? Wie geht es mit dem Treffen weiter? Eine Analyse in fünf Punkten.

https://www.tagesschau.de/inland/bilanz-sicherheitskonferenz-100.html

[EN] Europe is nervous about a potential Trump win. China sees an opportunity

China’s top diplomat Wang Yi had a message for his European counterparts over the weekend: no matter how the world changes, China will be “consistent and stable” – a “force for stability.”

https://edition.cnn.com/2024/02/19/asia/europe-is-nervous-about-a-potential-trump-win-china-sees-an-opportunity/index.html

[DE] #MSC2024-Nachlese mit Jana Puglierin

“Sicherheitshalber” ist der Podcast zur sicherheitspolitischen Lage in Deutschland, Europa und der Welt. In der schon traditionellen Spezial-Folge zur Münchner Sicherheitskonferenz (Munich Security Conference, MSC) blicken Ulrike Franke, Carlo Masala, Frank Sauer und Thomas Wiegold mit Jana Puglierin vom European Council on Foreign Relations (ECFR) auf das diesjährige Treffen in der bayerischen Landeshauptstadt. Und es gibt auch noch einen Überraschungsgast.

Amazon Scam

[DE] Wie eine Finanzkolumnistin in wenigen Stunden 50.000 Dollar verlor

Seien es Schockanrufe oder der »Tinder-Trading-Scam«: Viele Menschen halten sich für gewappnet gegen Betrugsmaschen. Der Fall einer New Yorker Journalistin jedoch zeigt, wie schnell die Vernunft aussetzen kann.

https://www.spiegel.de/netzwelt/web/betrug-im-internet-wie-eine-finanzkolumnistin-in-wenigen-stunden-50-000-dollar-verlor-a-4447bc80-52e4-409d-ac90-f8070198bcd3

[EN] The Day I Put $50,000 in a Shoe Box and Handed It to a Stranger

On a Tuesday evening this past October, I put $50,000 in cash in a shoe box, taped it shut as instructed, and carried it to the sidewalk in front of my apartment, my phone clasped to my ear…

https://www.thecut.com/article/amazon-scam-call-ftc-arrest-warrants.html

Weapons in space

[DE] Als die US-Armee Atombomben im Weltall testete

Anfang der 1960er-Jahre ließen die USA Atomwaffen in der äußeren Erdatmosphäre explodieren. Dabei offenbarte sich ein verheerender Effekt.

https://www.t-online.de/nachrichten/panorama/wissen/geschichte/id_100278408/us-atomtest-die-verheerenden-auswirkungen-der-atombombe-im-weltall-1962.html

[DE] Russland nukleare Anti-Satelliten-Waffen: „Müssen uns darauf einstellen, dass der Weltraum mit großer Dynamik militarisiert wird“

US-Geheimdienste haben Medienberichten zufolge Informationen über neue nukleare Ambitionen Russlands im Weltall zusammengetragen. „Im Weltraum beginnt langsam die Manöverkriegsführung“, warnt Oberst a.D. Ralph D. Thiele bei WELT-TV.

https://www.welt.de/politik/ausland/video250112160/Russland-nukleare-Anti-Satelliten-Waffen-Muessen-uns-darauf-einstellen-dass-der-Weltraum-mit-grosser-Dynamik-militarisiert-wird.html

[DE] Militarisierung des Weltraums und Marinemissionen in der Straße von Hormuz

Sicherheitshalber ist der Podcast zur sicherheitspolitischen Lage in Deutschland, Europa und der Welt. In Folge 16 sprechen Ulrike Franke, Frank Sauer, Carlo Masala und Thomas Wiegold zunächst über die zunehmende Militarisierung des Weltraums, also die jüngsten Entwicklungen in Sachen Anti-Satelliten-Waffen, Weltraumlaser und Präsident Trumps “Space Force”, aber auch über den Weltraumvertrag von 1967 und die Gefahren für die Raumfahrt durch Weltraumschrott.

[EN] Is Russia developing space-based nuclear weapon? What we know of US claim

What is the space-based nuclear weapon that the United States has warned Congress and allies in Europe that Russia could use against the West’s satellites?

https://www.reuters.com/world/what-is-space-based-nuclear-weapon-us-says-russia-is-developing-2024-02-15

[EN] ‘Everyone needs to calm down’: experts assess Russian nuclear space threat

Attacks in Earth’s orbit as likely to damage Russian interests as western ones, says leading academic

https://www.theguardian.com/world/2024/feb/15/experts-russian-nuclear-space-threat

[EN] Cost of nuclear war in space: Putting a weapon into orbit a military threat

Just before the Russian-Ukrainian war reached its two-year milestone today, US intelligence agencies warned that Russia might aim a nuclear weapon at an unusual target: not any place on Earth, but satellites orbiting in space.

https://www.business-standard.com/world-news/cost-of-nuclear-war-in-space-putting-a-weapon-into-orbit-a-military-threat-124022500697_1.html

Immer freue ich mich über Anregungen, Vorschläge und eure Meinung.

I am always happy about suggestions, proposals and your opinion.

Bleibt gesund und viele Grüße / Stay healthy and many greetings

Daniel

Categories
Uncategorized

Newsletter: Sicherheit, Digitales & Darüber Hinaus / Security, Digital & Beyond, #21

Remark (15.04.2023): This is an email newsletter, if you are interested send me a message.

08.04.2023

Einen schönen guten Tag,
und willkommen bei Sicherheit, Digitales & Darüber Hinaus, ein Newsletter mit den Themen aus der Cyber Sicherheit, Sicherheitspolitik.
Da ich viel lese, Online Kurse mache, Podcasts höre usw., führe ich seit langer Zeit Lese- und Merklisten. Inhalte, die mir weiterhelfen und von denen ich denke, dass sie für andere Menschen ebenfalls interessant sind, teile ich gerne.
Der Newsletter ist zweisprachig. Wo es möglich ist, versuche ich Artikel über ein Thema auf Deutsch und Englisch zu finden, und entsprechend zu kennzeichnen.
Immer freue ich mich über Anregungen, Vorschläge und Eure Meinung.

[EN] Have a nice day,
and welcome to Security, Digital & Beyond, a newsletter with the topics from cyber security, security policy and more.
Since I read a lot, do online courses, listen to podcasts, etc., I have been keeping reading and watch lists for a long time. I like to share content that helps me and that I think is interesting for other people as well.
The newsletter is bilingual. Where possible, I try to find articles about a topic in German and English and mark them accordingly.
I am always happy about suggestions, proposals and your opinion.

[DE] Managementkompass 01/2023 – BANI Navigieren in der neuen Normalität
Die Themen VUCA und BANI finde ich schon länger spannend. In dieser Ausgabe hatte ich die Freude ein Interview beizusteuern.
https://faz-bm.de/wp-content/uploads/sites/32/epaper/epaper-mk-bani-2023/epaper/ausgabe.pdf

Cybersecurity
[EN] MERCURY and DEV-1084: Destructive attack on hybrid environment
Microsoft Threat Intelligence has detected destructive operations enabled by MERCURY, a nation-state actor linked to the Iranian government, that attacked both on-premises and cloud environments. While the threat actors attempted to masquerade the activity as a standard ransomware campaign, the unrecoverable actions show destruction and disruption were the ultimate goals of the operation.
https://www.microsoft.com/en-us/security/blog/2023/04/07/mercury-and-dev-1084-destructive-attack-on-hybrid-environment/

[EN] Mandiant Catches Another North Korean Gov Hacker Group
Mandiant flags APT43 as a “moderately-sophisticated cyber operator that supports the interests of the North Korean regime.”
https://www.securityweek.com/mandiant-catches-another-north-korean-gov-hacker-group/

[EN] Indian defence agency bought spyware from Pegasus ‘rival’, trade data reveals
The spyware maker Cognyte, often billed as an alternative to Pegasus, has been selling tech gear to the Signal Intelligence Directorate which comes under the Ministry of Defence
https://www.thehindu.com/news/national/indian-defence-agency-bought-pegasus-rival-trade-data-reveals/article66701489.ece

[EN] Special Report: Tesla workers shared sensitive images recorded by customer cars

  • Private camera recordings, captured by cars, were shared in chat rooms: ex-workers
  • Circulated clips included one of child being hit by car: ex-employees
  • Tesla says recordings made by vehicle cameras ‘remain anonymous’
  • One video showed submersible vehicle from James Bond film, owned by Elon Musk

https://www.reuters.com/technology/tesla-workers-shared-sensitive-images-recorded-by-customer-cars-2023-04-06/

[DE] Ampel-Politiker fordern Ausschluss von Huawei bei der Deutschen Bahn
Im Zuge der Digitalisierung der Bahn sollen auch Komponenten des chinesischen Herstellers verbaut werden. Dagegen regt sich massiver Widerstand.
https://app.handelsblatt.com/politik/deutschland/kritische-infrastruktur-ampel-politiker-fordern-ausschluss-von-huawei-bei-der-deutschen-bahn/29081420.html

Sicherheitspolitik und mehr
Security Policy and more

[EN] Xi Jinping’s idea of world order
The real battle for international supremacy today is not between democracies and autocracies, but between different models of global order, with China and the West each offering its own distinct account of “democracy”. The sooner that Western leaders recognise this, the better chance they will have of attracting new partners
https://ecfr.eu/article/xi-jinpings-idea-of-world-order/

[DE] Wodka, Scholz und Gazprom
So feierten Nachwuchs-Lobbyisten für gute Geschäfte mit Russland – und befeuerten die Gas-Abhängigkeit.
https://correctiv.org/aktuelles/russland-ukraine-2/2023/04/03/wodka-scholz-und-gazprom/

[EN] China Is Eating Russia’s Lunch in the Defense Market
The script has flipped in the countries’ traditional defense-industrial relationship.
https://www.defenseone.com/ideas/2023/04/china-eating-russias-lunch-defense-market/384736/

[EN] Russian spies rebound in Europe
Critical infrastructure is a key target for Russia’s intelligence gathering, the priority being to monitor ‘the production and supply of Western arms to Ukraine.’
https://www.politico.eu/article/russia-spy-rebound-europe/

[EN] The Force is Female: 1st Lt. Samantha “FORCE” Colombo
“I ended up doing very well in my class of eight, I finished top of my class,” Colombo said. “The path and the amount of work you have to put in as a female compared to males is the exact same – learning the aircraft and flying it is the same. The biggest difference is more social. The comments and stereotypes make it more difficult.”
https://www.pacaf.af.mil/News/Article-Display/Article/3000481/the-force-is-female-1st-lt-samantha-force-colombo/

Podcast
[DE] Folge #70 Tāningupointo: Zeitenwende auf japanisch
“Sicherheitshalber” ist der Podcast zur sicherheitspolitischen Lage in Deutschland, Europa und der Welt. In Folge 70 sprechen Thomas Wiegold, Ulrike Franke, Frank Sauer und Carlo Masala mit der Japan-Kennerin und -Forscherin Alexandra Sakaki. Alexandra erklärt, welche Zeitenwende sich in Japan gerade vollzieht – denn auch dort wird sicherheitspolitisch gerade gezwungenermaßen massiv umgedacht. Von einer Verdopplung der Verteidigungsausgaben ist die Rede. Alexandra analysiert für die vier vom Sicherheitspod, was die Hintergründe und Implikationen sind und wie wahrscheinlich es eigentlich ist, dass das alles wirklich so kommt.
https://sicherheitspod.de/2023/04/05/70-taningupointo-zeitenwende-auf-japanisch/

ChatGPT
[DE] Italien sperrt ChatGPT
Italiens Datenschutzbehörde hat den KI-basierten Chatbot ChatGPT vorerst sperren lassen. Als Grund nannte sie Verstöße gegen den Daten- und Jugendschutz. Den Entwicklern der Software droht im Zweifel eine Millionenstrafe.
https://www.tagesschau.de/ausland/europa/italien-chatgpt-ki-101.html

[EN] ChatGPT banned in Italy over privacy concerns
Italy has become the first Western country to block advanced chatbot ChatGPT.
https://www.bbc.com/news/technology-65139406

[DE] Australischer Bürgermeister verklagt OpenAI wegen Verleumdung
Die einen lieben ChatGPT, die anderen hassen es. Und einer geht nun sogar gerichtlich gegen den generativen KI-Chatbot vor: Der Bürgermeister einer australischen Kleinstadt will die ChatGPT-Betreiber OpenAI wegen Verleumdung verklagen.
https://t3n.de/news/australischer-buergermeister-klage-verleumdung-chatgpt-1545973/

[EN] Australian mayor prepares world’s first defamation lawsuit over ChatGPT content
ChatGPT falsely identified Brian Hood as guilty party in foreign bribery scandal. In reality he blew the whistle on the illegal scheme
https://amp-theguardian-com.cdn.ampproject.org/c/s/amp.theguardian.com/technology/2023/apr/06/australian-mayor-prepares-worlds-first-defamation-lawsuit-over-chatgpt-content

[EN] ChatGPT invented a sexual harassment scandal and named a real law prof as the accused
The AI chatbot can misrepresent key facts with great flourish, even citing a fake Washington Post article as evidence
https://www.washingtonpost.com/technology/2023/04/05/chatgpt-lies/

[EN] Samsung workers made a major error by using ChatGPT
Samsung meeting notes and new source code are now in the wild after being leaked in ChatGPT
https://www.techradar.com/news/samsung-workers-leaked-company-secrets-by-using-chatgpt

[EN] Midjourney CEO Says ‘Political Satire In China Is Pretty Not Okay,’ But Apparently Silencing Satire About Xi Jinping Is Pretty Okay
https://www.techdirt.com/2023/03/31/midjourney-ceo-says-political-satire-in-china-is-pretty-not-okay-but-apparently-silencing-satire-about-xi-jinping-is-pretty-okay/

If you want to dig deep and start training your own language model.
[EN] GPT4All
Demo, data, and code to train an assistant-style large language model with ~800k GPT-3.5-Turbo Generations based on LLaMa
https://github.com/nomic-ai/gpt4all

Bleibt gesund und viele Grüße / Stay healthy and many greetings,
Daniel

Categories
Uncategorized

OpenAI, ChatGPT & beyond: Implications for future work, tech and everything

Like many I have been working with ChatGPT from OpenAI. For those who don’t know it yet, the following article is recommended:

https://en.wikipedia.org/wiki/ChatGPT

and

https://javascript.plainenglish.io/13-best-examples-of-chatgpt-on-the-internet-so-far-316876466d1c

Basically it’s a user can ask anything and it will come up with more or less meaningful answers. Some examples are very impressive. Homeworks and texts can be created with it, at least partially. But also program code.

I have the following example:

Q: Should a country only focus on defensive security in means of espionage and cyberwar?

A: While defensive security measures are an important part of protecting a country’s systems and information from cyber attacks, it is not advisable for a country to focus solely on defensive measures. This is because, in the realm of espionage and cyberwarfare, it is often necessary to take a more proactive approach in order to gather intelligence and maintain an advantage over potential adversaries. As such, a country that focuses only on defensive measures may find itself at a disadvantage, as it may be unable to gather the information it needs to protect itself or to gain an advantage in a potential conflict. Therefore, it is important for a country to balance its focus on defensive security measures with a more proactive approach to gathering intelligence and, if necessary, launching cyber attacks against potential adversaries.

So far, so good.

The problem, however, is that OpenAI has learned everything from texts on the Internet and can change the question or produce new texts until the answer fits or new answers can be generated. But this also means that biases and errors are reproduced in this way.

In self-learning systems it is also possible to manipulate results, an older example can be found here:

https://www.theverge.com/2016/3/24/11297050/tay-microsoft-chatbot-racist

To bring it to the point, it depends on WHAT you let your model learn so that it does something useful.

Historically I like to remind at this point of ELIZA (https://en.wikipedia.org/wiki/ELIZA) by Joseph Weizenbaum (https://en.wikipedia.org/wiki/Joseph_Weizenbaum) . If you want to go deeper into this topic you should read the book “The Power of Computers and the Powerlessness of Reason” (https://en.wikipedia.org/wiki/Computer_Power_and_Human_Reason):

Computer Power and Human Reason: From Judgment to Calculation (1976) by Joseph Weizenbaum displays the author’s ambivalence towards computer technology and lays out the case that while artificial intelligence may be possible, we should never allow computers to make important decisions because computers will always lack human qualities such as compassion and wisdom.

Of course, a lot has happened since then and the status is no longer comparable. Nevertheless, one should keep a critical eye on the development. Not only texts are created at the push of a button, but also images, avatars and perhaps soon videos. What that means, for example, in connection with deepfakes, I can’t imagine at the moment. Is it then soon or in the medium term possible to say:

“Make me a video on the politician X takes drugs.” Or similar, here also the holodeck of Star Trek comes to my mind, but of course it does not go so far yet. But imagine such a technology in the wrong hand and what it could mean for fakes, misinformation and other malicious activities.

Should videos and pictures be signed in the future to prove the origin? Does the same then perhaps apply to texts? How can trust be maintained on this basis?

The forecast that, for example, developers, journalists, etc. will no longer be needed in the future is difficult to share. Where else will new knowledge and ideas come from? In the end, everyone still has to get the maximum benefit from these new tools. As an example, perhaps a very short excursion into the chess world, many years ago hardly anyone would have thought that a computer would ever beat a chess grandmaster. But Deep Blue did it in 1996 (https://en.wikipedia.org/wiki/Deep_Blue_(chess_computer)), at that time it was a question of computing capacity and not a question of Machine Learning or Artificial Intelligence. Today skilled chess players play Internet games with computer support and analyze their other games (e.g. tournament games) afterwards with powerful chess engines to improve their play. The fact that such possibilities are also used for cheating shows how problematic this can be (https://www.spiegel.de/sport/schach-hans-niemann-verklagt-magnus-carlsen-wegen-betrugsvorwuerfen-a-5cc8e02f-3d5b-449c-a63d-b2dd20f0499a).

To ignore this development would be just like ignoring the Internet 20 years ago. So it can make sense to have texts or program code created and to use them because it simply saves time, not to mention the many other possibilities:

https://github.com/f/awesome-chatgpt-prompts

The new possibilities can also create completely new professions, and are already emerging. Conceivable to me are things like content manager AI/ML supported, trainer for models and certain purposes, AI supported technical development, automations, building systems to support experts and so on.

For further reading, here is another critical text on the subject which I found insightful:

Is ChatGPT a ‘virus that has been released into the wild’?

More than three years ago, this editor sat down with Sam Altman for a small event in San Francisco soon after he’d left his role as the president of Y Combinator to become CEO of the AI company he co-founded in 2015 with Elon Musk and others, OpenAI

https://techcrunch-com.cdn.ampproject.org/c/s/techcrunch.com/2022/12/09/is-chatgpt-a-virus-that-has-been-released-into-the-wild/amp/

Categories
Uncategorized

Slides Black Hat USA 2019

This time I prepared some slides, download here:
BHUSA19_Arsenal_AVET

Categories
Uncategorized

Slides – Introduction to AVET

Florian and I were at the root.cologne meet-up for giving an introduction to AVET:

Slides: avet introduction – root cologne

Interesting talks afterwards, nice location and pizza!

Now looking forward to black hat :).

Categories
Uncategorized

Wifi Hotspot with Windows 7

More a short note to myself… but might also be interesting for other folks.

You can make a Wifi Hotspot with Windows 7 with som cmd foo, but also with the programm Virtual Router Manager, which is easier:

2019-05-21 18_53_06-Virtual Router Manager v1.0.png

Download:

https://softfamous.com/virtual-router-manager/
https://www.pcwelt.de/downloads/Virtual-Router-Manager-583195.html

Or search on google…

Categories
Uncategorized

Windows 7 IE Developer SSH Server

Recently I played with one of the Windows 7 32Bit IE Developer VMs (IE11.Win7.VirtualBox.zip) from here. I can remember two exploitation classes where these machines are being used.

I found an SSH server installed within the machine, it is not hidden or something, but on the other side no one I asked was aware about it.

As you can see the server is running on port 22:

iewin7_netstat.png

The SSH server itself is running with its own user:

iewin7_sshuser.png

The SSH service is not blocked by local firewall rules:

iewin7_login.png

Short reminder, the password is “Passw0rd!”. So better use these machines in NAT mode, change the password, adjust firewall etc..

Happy Hacking.

Categories
Uncategorized

A new project: welearnsecurity.com

Here is my new project:
https://welearnsecurity.com/.
I love to write for career starters and also working with them. Since the content is too different from this blog I decided to split the content.
The blog will go from personal career experience to idealized career paths, hopefully articles or interviews from/with other successful security experts, recommendations for books and courses and so on.
Hopefully this project will become a valuable source for everyone looking into a career in infosec and motivated learners.