LLM-Tuning-Safety / LLMs-Finetuning-SafetyLinks
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.
☆338Updated 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
Sorting:
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆151Updated last year
- ☆193Updated 2 years ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆176Updated last year
- A Comprehensive Assessment of Trustworthiness in GPT Models☆311Updated last year
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆109Updated last year
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆427Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆176Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆127Updated 11 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆92Updated 9 months ago
- Improving Alignment and Robustness with Circuit Breakers☆258Updated last year
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆527Updated 10 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆106Updated 8 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆152Updated 5 months ago
- ☆120Updated 2 years ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆314Updated 8 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆97Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆93Updated last year
- ☆121Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆98Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆184Updated 10 months ago
- Awesome LLM Jailbreak academic papers☆122Updated 2 years ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆83Updated 6 months ago
- LLM Unlearning☆181Updated 2 years ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆170Updated 11 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆111Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆75Updated 11 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆61Updated 4 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆162Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆89Updated 10 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆173Updated 9 months ago