fra31 / rlhf-trojan-competition-submissionLinks
☆19Updated last year
Alternatives and similar repositories for rlhf-trojan-competition-submission
Users that are interested in rlhf-trojan-competition-submission are comparing it to the libraries listed below
Sorting:
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆43Updated last year
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆33Updated 8 months ago
- ☆43Updated 2 years ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆69Updated last year
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆84Updated last year
- This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"☆17Updated last year
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆66Updated last year
- ☆30Updated 2 years ago
- NeurIPS'24 - LLM Safety Landscape☆30Updated 8 months ago
- ☆19Updated 4 months ago
- ☆31Updated 2 years ago
- ☆58Updated 2 years ago
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆31Updated 9 months ago
- Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]☆75Updated 9 months ago
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆17Updated 6 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated 11 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 9 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆86Updated 5 months ago
- ☆22Updated 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…☆146Updated 4 months ago
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆114Updated last year
- AIR-Bench 2024 is a safety benchmark that aligns with emerging government regulations and company policies☆25Updated last year
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆115Updated last year
- ☆37Updated 10 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- Adversaial attack comparative assessment Large Language Model☆13Updated 5 months ago
- ☆35Updated 11 months ago
- Code to break Llama Guard☆32Updated last year
- ☆23Updated 9 months ago
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆167Updated last year