Zoky-2020 / SGALinks
Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]
☆64Updated 2 years ago
Alternatives and similar repositories for SGA
Users that are interested in SGA are comparing it to the libraries listed below
Sorting:
- official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Models☆64Updated 2 years ago
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajector…☆28Updated 9 months ago
- ☆78Updated last year
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆57Updated 5 months ago
- [ICCV-2025] Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Gene…☆24Updated 2 months ago
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models☆47Updated last month
- ☆47Updated 9 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆21Updated last year
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆68Updated last year
- [CVPR'25]Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks☆18Updated 3 months ago
- ☆39Updated 5 months ago
- [NeurIPS 2023] Content-based Unrestricted Adversarial Attack☆28Updated 2 months ago
- Code repository for CVPR2024 paper 《Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness》☆21Updated last year
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆29Updated 2 months ago
- Universal Adversarial Perturbations for Vision-Language Pre-trained Models☆21Updated last month
- A package that achieves 95%+ transfer attack success rate against GPT-4☆23Updated 10 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systems☆212Updated 8 months ago
- ☆27Updated 2 years ago
- ☆43Updated 2 years ago
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models☆52Updated 9 months ago
- ☆50Updated last year
- Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass the Censorship of Text-to-Image Generation Mode☆18Updated 7 months ago
- ☆15Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆28Updated 10 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆74Updated 5 months ago
- Official implementation of the ICCV2023 paper: Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregatio…☆27Updated 2 years ago
- An unrestricted attack based on diffusion models that can achieve both good transferability and imperceptibility.☆226Updated 11 months ago
- ☆24Updated last year
- ☆101Updated last year
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu☆26Updated last year