thu-ml / STAIR
Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"
☆28Updated last month
Alternatives and similar repositories for STAIR:
Users that are interested in STAIR are comparing it to the libraries listed below
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆78Updated last year
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆54Updated 8 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆44Updated 2 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆82Updated 8 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆61Updated 2 months ago
- Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆35Updated 2 weeks ago
- Accepted by ECCV 2024☆115Updated 5 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆51Updated 8 months ago
- ☆21Updated 2 weeks ago
- Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as …☆53Updated this week
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆41Updated 4 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆73Updated last month
- A package that achieves 95%+ transfer attack success rate against GPT-4☆17Updated 5 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆59Updated 2 months ago
- An implementation for MLLM oversensitivity evaluation☆10Updated 4 months ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆21Updated this week
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆45Updated 9 months ago
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆35Updated 11 months ago
- ☆33Updated 9 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆23Updated 4 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆20Updated 8 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆25Updated 8 months ago
- ☆32Updated 3 months ago
- Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?☆21Updated last month
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆36Updated 5 months ago
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"☆22Updated 5 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆48Updated 11 months ago
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆30Updated 4 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆73Updated last year
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆140Updated last week