ZhangHangTao / Awesome-Embodied-AI-Safety
Focused on the safety and security of Embodied AI
β17Updated last week
Alternatives and similar repositories for Awesome-Embodied-AI-Safety:
Users that are interested in Awesome-Embodied-AI-Safety are comparing it to the libraries listed below
- official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Modelsβ59Updated 2 years ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]β58Updated last year
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β45Updated 9 months ago
- [NeurIPS 2023] Content-based Unrestricted Adversarial Attackβ24Updated last year
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β50Updated last week
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectorβ¦β24Updated 4 months ago
- β40Updated 3 months ago
- Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Generator, Generβ¦β15Updated 5 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ32Updated last year
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ186Updated 3 months ago
- Universal Adversarial Perturbations for Vision-Language Pre-trained Modelsβ13Updated this week
- β68Updated 8 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussionsβ59Updated 7 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β27Updated 5 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdfβ19Updated last year
- β34Updated 2 years ago
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacksβ16Updated this week
- β19Updated 6 months ago
- [ACM MM2023] Code Release of GCMA: Generative Cross-Modal Transferable Adversarial Attacks from Images to Videosβ12Updated last year
- Summaries of ICML 2024 papersβ10Updated 7 months ago
- π up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.β249Updated last week
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Modelsβ144Updated this week
- AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models (ICCV 2023)β18Updated last year
- β43Updated 7 months ago
- [ICCV 2023] Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Promptingβ15Updated last year
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Modelsβ47Updated 3 months ago
- β40Updated last year
- Adversarial Examples Detection Benchmarkβ10Updated 3 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion modelsβ62Updated last week
- β45Updated 3 months ago