thu-ml / STAIRLinks
Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"
☆75Updated 8 months ago
Alternatives and similar repositories for STAIR
Users that are interested in STAIR are comparing it to the libraries listed below
Sorting:
- Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as …☆74Updated this week
- Official repository for "Safety in Large Reasoning Models: A Survey" - Exploring safety risks, attacks, and defenses for Large Reasoning …☆75Updated 2 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆157Updated 6 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆168Updated 4 months ago
- Accepted by ECCV 2024☆165Updated last year
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆77Updated 9 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆85Updated 6 months ago
- ☆63Updated 6 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆53Updated 3 weeks ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆83Updated last year
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆51Updated 3 months ago
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL☆46Updated last month
- ☆50Updated 4 months ago
- ☆108Updated 8 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆65Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆62Updated 7 months ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆32Updated 7 months ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆47Updated 11 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 9 months ago
- ☆30Updated 6 months ago
- The reinforcement learning codes for dataset SPA-VL☆39Updated last year
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆33Updated 11 months ago
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆110Updated 8 months ago
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆32Updated 5 months ago
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆52Updated last month
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆79Updated 5 months ago
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆45Updated 2 weeks ago
- This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".☆26Updated 7 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆32Updated last year
- [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".☆28Updated 2 months ago