thu-ml / STAIR
Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"
☆34Updated 2 months ago
Alternatives and similar repositories for STAIR:
Users that are interested in STAIR are comparing it to the libraries listed below
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆145Updated last month
- Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as …☆63Updated this week
- Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆37Updated last month
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆70Updated 3 months ago
- Accepted by ECCV 2024☆127Updated 6 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆80Updated last year
- ☆41Updated last month
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆10Updated 6 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆76Updated last month
- ☆81Updated 3 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆57Updated 9 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆12Updated 6 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆19Updated 6 months ago
- 🔥🔥🔥Breaking long thought processes of o1-like LLMs, such as DeepSeek-R1, QwQ☆28Updated 2 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆61Updated 3 months ago
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆36Updated last year
- An implementation for MLLM oversensitivity evaluation☆13Updated 5 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆46Updated 3 months ago
- The reinforcement learning codes for dataset SPA-VL☆32Updated 10 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆110Updated last week
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆42Updated 5 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆57Updated 2 weeks ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆52Updated 2 months ago
- ☆26Updated 6 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆19Updated 9 months ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆25Updated last month
- ☆31Updated last month
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆23Updated 6 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆38Updated 6 months ago
- ☆27Updated 10 months ago