RylanSchaeffer / AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer
Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?
☆22Updated 2 months ago
Alternatives and similar repositories for AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer
Users that are interested in AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer are comparing it to the libraries listed below
Sorting:
- ☆40Updated 11 months ago
- ☆41Updated last month
- A package that achieves 95%+ transfer attack success rate against GPT-4☆19Updated 6 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆23Updated last year
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆19Updated 9 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆19Updated 6 months ago
- Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models☆16Updated 7 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆52Updated 11 months ago
- ☆23Updated 3 weeks ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆12Updated last week
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆29Updated 4 months ago
- ☆13Updated 2 months ago
- 🔥🔥🔥Breaking long thought processes of o1-like LLMs, such as DeepSeek-R1, QwQ☆29Updated 2 months ago
- ☆42Updated 5 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆51Updated 9 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆53Updated 2 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆39Updated 6 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆46Updated 4 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆22Updated 10 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆60Updated last week
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆47Updated last year
- ☆45Updated 9 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆26Updated 4 months ago
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆17Updated 6 months ago
- ☆19Updated 11 months ago
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆9Updated 6 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆80Updated last year
- ☆52Updated 4 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆53Updated last year
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆71Updated 3 months ago