centerforaisafety / wmdpLinks
WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining general capabilities.
☆128Updated last month
Alternatives and similar repositories for wmdp
Users that are interested in wmdp are comparing it to the libraries listed below
Sorting:
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆101Updated 4 months ago
- Improving Alignment and Robustness with Circuit Breakers☆218Updated 9 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆59Updated last month
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆157Updated 6 months ago
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆307Updated last year
- ☆175Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆85Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆62Updated 6 months ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆113Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆157Updated last year
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆77Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆76Updated 2 months ago
- A Comprehensive Assessment of Trustworthiness in GPT Models☆294Updated 10 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆94Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆56Updated 4 months ago
- ☆72Updated last week
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆80Updated 3 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆135Updated 11 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆95Updated last year
- ☆55Updated 2 years ago
- A resource repository for representation engineering in large language models☆127Updated 8 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆90Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆74Updated 4 months ago
- General-purpose activation steering library☆83Updated 2 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆64Updated last year
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆84Updated 7 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆69Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆58Updated 2 weeks ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆68Updated 8 months ago
- Steering Llama 2 with Contrastive Activation Addition☆162Updated last year