thu-ml / STAIRLinks
Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"
☆87Updated 9 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 …☆78Updated this week
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆170Updated 5 months ago
- Accepted by ECCV 2024☆176Updated last year
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆80Updated 10 months ago
- Official repository for "Safety in Large Reasoning Models: A Survey" - Exploring safety risks, attacks, and defenses for Large Reasoning …☆81Updated 3 months ago
- ☆66Updated 8 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆55Updated 2 months ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆33Updated 8 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆166Updated 7 months ago
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆52Updated 4 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆87Updated 8 months ago
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL☆52Updated 3 months ago
- ☆58Updated 6 months ago
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆32Updated 6 months ago
- The reinforcement learning codes for dataset SPA-VL☆42Updated last year
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆67Updated last year
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆57Updated 2 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆84Updated 2 years ago
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆46Updated last month
- ☆112Updated 10 months ago
- [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".☆30Updated 4 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆82Updated 6 months ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆48Updated last year
- [AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data☆32Updated 7 months ago
- ☆30Updated 8 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆34Updated last year
- ☆42Updated 3 weeks ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆78Updated last year
- An implementation for MLLM oversensitivity evaluation☆17Updated last year
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆57Updated 10 months ago