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.
☆145Updated 4 months ago
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"☆116Updated 7 months ago
- Improving Alignment and Robustness with Circuit Breakers☆236Updated last year
- ☆184Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆61Updated 4 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆87Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆166Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆166Updated 9 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…☆323Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆62Updated 7 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆144Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 9 months ago
- A Comprehensive Assessment of Trustworthiness in GPT Models☆303Updated last year
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆114Updated last year
- NeurIPS'24 - LLM Safety Landscape☆30Updated 7 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆83Updated last year
- ☆31Updated 2 years ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆86Updated 5 months ago
- ☆101Updated 3 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆70Updated 2 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆98Updated 2 years ago
- ☆58Updated 2 years ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆98Updated last year
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆69Updated last year
- A re-implementation of the "Red Teaming Language Models with Language Models" paper by Perez et al., 2022☆34Updated 2 years ago
- ☆24Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆108Updated 7 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆65Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆170Updated 6 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆71Updated 11 months ago
- A resource repository for representation engineering in large language models☆136Updated 10 months ago