Paper 15

B-DENSE: Branching for Dense Ensemble Network Supervision Efficiency

An efficient supervision strategy that uses branching in dense ensemble networks to improve training efficiency while preserving predictive performance.

ICLR
Paper 14

Verifiability-First Agents: Provable Observability and Lightweight Audit Agents for Controlling Autonomous LLM Systems

An architecture with built-in attestations, audit agents, and challenge-response checks, alongside OPERA to benchmark detection and remediation of agent misalignment

AAAI
Paper 13

DAC-LoRA: Dynamic Adversarial Curriculum for Efficient and Robust Few-Shot Adaptation

A generalized framework that uses a dynamic, adversarial curriculum to make Vision-Language Models (VLMs) more robust against attacks, improving efficiency and few-shot adaptation

ICCV
Paper 12

DINOHash: Learning Adversarially Robust Perceptual Hashes from Self-Supervised Features

An open-source framework for robust perceptual image hashing, DINOHash enables secure and transformation-resilient provenance detection of AI-generated images.

ICML
Paper 11

SPD Attack - Prevention of AI Powered Image Editing by Image Immunization

An analysis of methods to safeguard images against misuse in image-to-image editing models through reproduction and extension of existing research across various models and datasets.

ICLR
Paper 10

From Teacher to Student: Tracking Memorization Through Model Distillation

An analysis of knowledge distillation effects on memorization in fine-tuned language models, showing that distillation from large teachers to smaller students mitigates memorization risks while improving efficiency.

ACL
Paper 9

Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models

In this study, we conduct a comprehensive reproducibility study of "An Image is Worth 1000 Lies: Adversarial Transferability Across Prompts on Vision-Language Models" validating the Cross-Prompt Attack (CroPA), and also proposing several key improvements to the framework.

TMLR
Paper 8

[Re] CUDA: Curriculum of Data Augmentation for Long‐tailed Recognition

Using classwise degree of data augmentation to tackle class imbalance in long tailed dataset

MLRC
Paper 7

Riemann Sum Optimization for Accurate Integrated Gradients Computation

A mathematical framework to reduce computational complexity of Integrated Gradients

NeurIPS
Paper 6

Strengthening Interpretability: An Investigative Study of Integrated Gradient Methods

This study reproduces IDGI, showing reduced noise and better stability than Integrated Gradients, while analyzing the effect of step size.

TMLR
Paper 5

Rethinking Randomized Smoothing from the Perspective of Scalability

A study on randomized smoothing, analysed from the perspective of scalability as a challenge to its continued application

NeurIPS
Paper 4

Image-Alchemy: Advancing Subject Fidelity in Personalized Text-to-Image Generation

A two-stage personalization pipeline for personalized image generation using LoRA-based attention fine-tuning and segmentation-guided Img2Img synthesis.

ICLR
Paper 3

Detection Limits and Statistical Separability of Tree Ring Watermarks in Rectified Flow-based Text-to-Image Generation Models

Tree Ring Watermarks are harder to detect in modern rectified flow-based models compared to traditional diffusion models, especially under image attacks.

ICLR
Paper 2

One Noise to Fool Them All: Universal Adversarial Defenses Against Image Editing

Image immunization involves adding undetectable noise in images to prevent editing via diffusion models. We further extended this to multiple images using a single noise.

CVPR
Paper 1

Impact of Language Guidance: A Reproducibility Study

A reproducability study of Language guidance on self-supervised learning frameworks

ArXiv