Pinned Loading

1. CROW CROW Public

   Internal Consistency Regularization (CROW) for LLM Backdoor Elimination - Paper accepted to ICML 2025

   Python 12

2. ULRL ULRL Public

   Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning

   Python 2

3. RAVEN-AI RAVEN-AI Public

   Response Anomaly Vigilance for Uncovering Semantic Inconsistencies

   Python 1

4. BackdoorLLM BackdoorLLM Public

   Forked from bboylyg/BackdoorLLM

   BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models

   Python

5. semantic_uncertainty_for_backdoor semantic_uncertainty_for_backdoor Public

   Codebase for RAVEN

   Python

6. simple-finetune simple-finetune Public

   Using llamafactory to simply finetune LLM models for my experiments

   Python