Pinned Loading

1. lancopku/Embedding-Poisoning lancopku/Embedding-Poisoning Public

   Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-HLT 2021)

   Python 43 7

2. lancopku/SOS lancopku/SOS Public

   Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)

   Jupyter Notebook 24 4

3. lancopku/RAP lancopku/RAP Public

   Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)

   Python 26 2

4. lancopku/agent-backdoor-attacks lancopku/agent-backdoor-attacks Public

   Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]

   Python 103 5

5. weak-to-strong-deception weak-to-strong-deception Public

   [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"

   Python 13

6. RUCBM/DeepCritic RUCBM/DeepCritic Public

   Official repository for paper "DeepCritic: Deliberate Critique with Large Language Models"

   Python 40