JonasGeiping / carvingLinks
Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
☆70Updated last year
Alternatives and similar repositories for carving
Users that are interested in carving are comparing it to the libraries listed below
Sorting:
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆53Updated 11 months ago
- ☆41Updated 10 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆64Updated last year
- ☆55Updated 2 years ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆114Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆64Updated 6 months ago
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆43Updated last year
- Code to break Llama Guard☆31Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆59Updated last month
- ☆31Updated 2 years ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆90Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆106Updated 5 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆96Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆62Updated last week
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆81Updated 9 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆84Updated 3 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆57Updated last year
- Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting☆18Updated 3 months ago
- Improving Alignment and Robustness with Circuit Breakers☆225Updated 10 months ago
- ☆178Updated last year
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆132Updated 2 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆160Updated 7 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆160Updated last year
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆69Updated 9 months ago
- Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]☆70Updated 6 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆87Updated 8 months ago
- ☆35Updated 7 months ago
- ☆104Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆51Updated 9 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆56Updated 11 months ago