BeyonderXX / ShadowAlignment
Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models
☆23Updated last year
Related projects ⓘ
Alternatives and complementary repositories for ShadowAlignment
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆69Updated 2 months ago
- ☆34Updated 3 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆13Updated 4 months ago
- Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆58Updated last month
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆46Updated last month
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆59Updated 8 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆23Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆83Updated 5 months ago
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆58Updated last month
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆16Updated 2 weeks ago
- LLM Unlearning☆123Updated last year
- ☆31Updated 4 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆103Updated 3 weeks ago
- Official code for the paper: Evaluating Copyright Takedown Methods for Language Models☆15Updated 3 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆70Updated 6 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆64Updated 8 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆21Updated 4 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆41Updated last month
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆60Updated 7 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆26Updated 4 months ago
- ☆15Updated 3 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆60Updated last month
- ☆33Updated last year
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆61Updated 8 months ago
- ☆25Updated last month
- Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting☆12Updated 7 months ago
- ☆38Updated last week
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆111Updated last year
- Accepted by ECCV 2024☆71Updated 3 weeks ago
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆76Updated 3 months ago