thu-ml / Attack-BardLinks
☆109Updated last year
Alternatives and similar repositories for Attack-Bard
Users that are interested in Attack-Bard are comparing it to the libraries listed below
Sorting:
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systems☆227Updated last year
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆42Updated 2 years ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆59Updated last year
- A package that achieves 95%+ transfer attack success rate against GPT-4☆26Updated last year
- ☆55Updated last year
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆66Updated 10 months ago
- ☆57Updated last year
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆79Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆34Updated last year
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆54Updated 2 years ago
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models☆66Updated 6 months ago
- ☆58Updated last year
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆60Updated last year
- ☆71Updated 10 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆174Updated 7 months ago
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (NeurIPS 2025)☆46Updated 3 months ago
- ☆80Updated last year
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆35Updated last week
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models☆266Updated last year
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆59Updated 5 months ago
- Accept by CVPR 2025 (highlight)☆22Updated 8 months ago
- [NeurIPS25 & ICML25 Workshop on Reliable and Responsible Foundation Models] A Simple Baseline Achieving Over 90% Success Rate Against the…☆86Updated last week
- ☆47Updated last year
- Accepted by ECCV 2024☆186Updated last year
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆191Updated 7 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆22Updated 9 months ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆86Updated 11 months ago
- ☆25Updated last year
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆31Updated last year
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆90Updated last month