AoiDragon / HADESLinks
[ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models''
β34Updated 10 months ago
Alternatives and similar repositories for HADES
Users that are interested in HADES are comparing it to the libraries listed below
Sorting:
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β65Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β27Updated 10 months ago
- β46Updated 8 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"β81Updated last year
- β50Updated last year
- β58Updated 4 months ago
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignmentβ22Updated 2 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β74Updated 7 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β62Updated last year
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β56Updated 5 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)β30Updated 9 months ago
- [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Modelsβ140Updated 2 months ago
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Modelsβ50Updated 8 months ago
- β47Updated last year
- [ICCV-2025] Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Geneβ¦β24Updated last month
- β37Updated last year
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Modelsβ55Updated last year
- β102Updated last year
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β52Updated 7 months ago
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreβ¦β35Updated last month
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ209Updated 8 months ago
- Accepted by ECCV 2024β149Updated 10 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ163Updated 2 months ago
- [NAACL 2025 Main] Official Implementation of MLLMU-Benchβ31Updated 5 months ago
- β23Updated last year
- Code for the paper "Jailbreak Large Vision-Language Models Through Multi-Modal Linkage"β15Updated 8 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β162Updated 2 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ38Updated last year
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtimeβ50Updated last year
- A package that achieves 95%+ transfer attack success rate against GPT-4β23Updated 10 months ago