LLM-Tuning-Safety / LLMs-Finetuning-Safety
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 via OpenAI’s APIs.
☆290Updated last year
Alternatives and similar repositories for LLMs-Finetuning-Safety:
Users that are interested in LLMs-Finetuning-Safety are comparing it to the libraries listed below
- ☆170Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆129Updated 9 months ago
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆319Updated 3 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆151Updated 11 months ago
- Improving Alignment and Robustness with Circuit Breakers☆196Updated 7 months ago
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆94Updated 8 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆332Updated 3 weeks ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆80Updated 11 months ago
- ☆81Updated 2 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆142Updated last month
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆90Updated 7 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆95Updated 2 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆134Updated 2 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆102Updated 3 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆165Updated 4 months ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆225Updated 2 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆97Updated last year
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆136Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆148Updated 3 weeks ago
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models☆217Updated 11 months ago
- Awesome LLM Jailbreak academic papers☆93Updated last year
- ☆97Updated last year
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆52Updated 7 months ago
- Papers about red teaming LLMs and Multimodal models.☆109Updated 5 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆72Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆91Updated 11 months ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆135Updated last year
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆141Updated last year
- A survey on harmful fine-tuning attack for large language model☆159Updated last week
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆110Updated 11 months ago