wang2226 / Trojan-Activation-Attack
[CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.
☆23Updated 9 months ago
Alternatives and similar repositories for Trojan-Activation-Attack
Users that are interested in Trojan-Activation-Attack are comparing it to the libraries listed below
Sorting:
- ☆27Updated 7 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆23Updated last year
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆22Updated 10 months ago
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆39Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆72Updated 7 months ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆34Updated 9 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆53Updated 2 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆39Updated 6 months ago
- This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Lang…☆17Updated 10 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 6 months ago
- ☆85Updated 3 months ago
- ☆23Updated 6 months ago
- ☆18Updated 11 months ago
- Unofficial implementation of "Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection"☆18Updated 10 months ago
- ☆48Updated 11 months ago
- ☆18Updated 8 months ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆21Updated 5 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆51Updated 9 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆62Updated 6 months ago
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆36Updated 6 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆19Updated 9 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆33Updated last year
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆31Updated 4 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆82Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆91Updated 8 months ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆16Updated last year
- ☆21Updated 2 months ago
- ☆21Updated last year
- ☆20Updated last year
- This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".☆16Updated 2 months ago