AoiDragon / HADES
[ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models''
β24Updated 5 months ago
Alternatives and similar repositories for HADES:
Users that are interested in HADES are comparing it to the libraries listed below
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β45Updated 9 months ago
- β32Updated 3 months ago
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Modelsβ46Updated 3 months ago
- β40Updated 3 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"β77Updated last year
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)β22Updated 4 months ago
- β42Updated 7 months ago
- β31Updated 8 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β59Updated 2 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β50Updated 4 months ago
- β32Updated 9 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Modelsβ50Updated 11 months ago
- β40Updated last year
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β42Updated 2 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β16Updated 4 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β52Updated 8 months ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsβ¦β72Updated 2 weeks ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ30Updated last year
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liuβ26Updated 6 months ago
- Official implementation of NeurIPS'24 paper "Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Modelβ¦β39Updated 4 months ago
- Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Generator, Generβ¦β14Updated 5 months ago
- The official repository for paper "MLLM-Protector: Ensuring MLLMβs Safety without Hurting Performance"β34Updated 10 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β17Updated 4 months ago
- ECCV2024: Adversarial Prompt Tuning for Vision-Language Modelsβ24Updated 4 months ago
- The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?β27Updated 4 months ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]β57Updated last year
- β27Updated 2 months ago
- Accepted by ECCV 2024β110Updated 5 months ago
- β19Updated 6 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ186Updated 2 months ago