thu-ml / STAIRLinks
Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"
☆88Updated 11 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 …☆81Updated this week
- Official repository for "Safety in Large Reasoning Models: A Survey" - Exploring safety risks, attacks, and defenses for Large Reasoning …☆85Updated 5 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆84Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆170Updated 9 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆58Updated 3 months ago
- Accepted by ECCV 2024☆181Updated last year
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆174Updated 7 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆89Updated 9 months ago
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL☆59Updated 4 months ago
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆53Updated 6 months ago
- ☆70Updated 9 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆86Updated 2 years ago
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆58Updated 4 months ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆36Updated 10 months ago
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆32Updated 8 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆69Updated last year
- The reinforcement learning codes for dataset SPA-VL☆44Updated last year
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆58Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆122Updated 11 months ago
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆47Updated 3 months ago
- [AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data☆33Updated 9 months ago
- ☆121Updated 11 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆85Updated 8 months ago
- ☆63Updated 7 months ago
- ☆25Updated 10 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆29Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆74Updated 10 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆60Updated last year
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆78Updated last year
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆32Updated last year