thunxxx / MLLM-Jailbreak-evaluation-MMJ-Bench
β22Updated 2 weeks ago
Related projects β
Alternatives and complementary repositories for MLLM-Jailbreak-evaluation-MMJ-Bench
- Accepted by ECCV 2024β74Updated last month
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β26Updated 5 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β45Updated 3 months ago
- β24Updated 5 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β15Updated last month
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"β67Updated 11 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)β16Updated 3 weeks ago
- β37Updated 3 months ago
- β30Updated 5 months ago
- β26Updated 4 months ago
- Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ87Updated 6 months ago
- JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess β¦β35Updated 4 months ago
- [Arxiv 2024] Adversarial attacks on multimodal agentsβ40Updated 4 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β14Updated last month
- Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?β15Updated this week
- β17Updated 5 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β108Updated 2 weeks ago
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtimeβ38Updated last year
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β40Updated 3 weeks ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ24Updated 9 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794β¦β12Updated 3 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β45Updated 4 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β20Updated last month
- β24Updated last week
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β28Updated last month
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completionβ29Updated 3 weeks ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Modelsβ44Updated 7 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ162Updated last year
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"β20Updated last year
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"β14Updated last month