facebookresearch / SecAlign
Repo for the research paper "Aligning LLMs to Be Robust Against Prompt Injection"
☆18Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for SecAlign
- ☆31Updated last year
- ☆14Updated 6 months ago
- Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting☆12Updated 3 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆63Updated 8 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆57Updated 9 months ago
- ☆49Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆59Updated this week
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆32Updated 2 weeks ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆44Updated last month
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆46Updated 2 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆83Updated 5 months ago
- [Arxiv 2024] Adversarial attacks on multimodal agents☆38Updated 4 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆46Updated 3 months ago
- Official Repository for Dataset Inference for LLMs☆23Updated 3 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆81Updated 6 months ago
- ☆13Updated 3 weeks ago
- [SafeGenAi @ NeurIPS 2024] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates☆60Updated 2 weeks ago
- ☆38Updated last year
- ☆26Updated 2 weeks ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆97Updated 3 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆44Updated last week
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆17Updated 8 months ago
- Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]☆19Updated 6 months ago
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆42Updated 6 months ago
- Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆38Updated 3 weeks ago
- Code for "Universal Adversarial Triggers Are Not Universal."☆15Updated 6 months ago
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆61Updated 10 months ago
- ☆39Updated last week
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆26Updated 4 months ago
- LLM Self Defense: By Self Examination, LLMs know they are being tricked☆26Updated 5 months ago