thu-coai / AISafetyLab
AISafetyLab: A comprehensive framework covering safety attack, defense, evaluation and paper list.
☆23Updated this week
Alternatives and similar repositories for AISafetyLab:
Users that are interested in AISafetyLab are comparing it to the libraries listed below
- Accepted by ECCV 2024☆92Updated 3 months ago
- ☆70Updated last week
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆60Updated 4 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆45Updated 6 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆104Updated last month
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆23Updated 6 months ago
- ☆40Updated 5 months ago
- ☆27Updated last month
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆34Updated 3 months ago
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆42Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆16Updated 3 months ago
- ☆33Updated last month
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆49Updated 6 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆17Updated 3 months ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆33Updated 2 months ago
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆28Updated 2 weeks ago
- [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacks☆13Updated 11 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆76Updated last year
- ☆37Updated 7 months ago
- ☆16Updated 7 months ago
- A survey on harmful fine-tuning attack for large language model☆129Updated 2 weeks ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆18Updated 6 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆37Updated 7 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆18Updated 6 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆83Updated 4 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆48Updated 5 months ago
- ☆29Updated 7 months ago
- Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆28Updated 2 weeks ago
- The repository of the paper "REEF: Representation Encoding Fingerprints for Large Language Models," aims to protect the IP of open-source…☆35Updated 2 weeks ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆67Updated 6 months ago