jiaxiaojunQAQ / FOA-AttackLinks
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (NeurIPS 2025)
☆41Updated last month
Alternatives and similar repositories for FOA-Attack
Users that are interested in FOA-Attack are comparing it to the libraries listed below
Sorting:
- Code repository for the paper "Heuristic Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models"☆14Updated 4 months ago
- Accept by CVPR 2025 (highlight)☆21Updated 6 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆25Updated last year
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆32Updated 5 months ago
- ☆52Updated last year
- ☆54Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆32Updated last year
- ☆23Updated last year
- ☆80Updated last year
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆24Updated last year
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆63Updated 8 months ago
- The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)☆13Updated last year
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆41Updated last year
- ☆107Updated last year
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models☆60Updated 4 months ago
- Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass the Censorship of Text-to-Image Generation Mode☆18Updated 9 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆21Updated 7 months ago
- A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation☆40Updated this week
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆14Updated 5 months ago
- Code for Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks (TIFS2024)☆13Updated last year
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆31Updated 3 months ago
- ☆65Updated 8 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆84Updated 8 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆57Updated 10 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆77Updated last year
- ☆45Updated 8 months ago
- [ICCV-2025] Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Gene…☆31Updated 5 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆30Updated 11 months ago
- ☆52Updated last year
- Official repository for "On the Multi-modal Vulnerability of Diffusion Models"☆16Updated last year