BeyonderXX / ShadowAlignmentLinks
Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models
☆29Updated last year
Alternatives and similar repositories for ShadowAlignment
Users that are interested in ShadowAlignment are comparing it to the libraries listed below
Sorting:
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆92Updated last month
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆94Updated last year
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆29Updated 11 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆80Updated 3 months ago
- ☆41Updated 9 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆29Updated last year
- 【ACL 2024】 SALAD benchmark & MD-Judge☆154Updated 4 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆77Updated last year
- ☆16Updated 3 weeks ago
- ☆33Updated 9 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆85Updated last year
- ☆91Updated 5 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆55Updated 11 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆26Updated last year
- ☆60Updated last year
- ☆21Updated 3 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆76Updated 2 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆56Updated 4 months ago
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆104Updated 11 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆137Updated 2 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆157Updated last year
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆52Updated 2 years ago
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆42Updated 8 months ago
- LLM Unlearning☆171Updated last year
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆20Updated 11 months ago
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆77Updated 9 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆101Updated 4 months ago
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆34Updated 6 months ago
- [ICLR 2025] A Closer Look at Machine Unlearning for Large Language Models☆32Updated 7 months ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆148Updated last year