ZhangHangTao / Awesome-Embodied-AI-Safety
Focused on the safety and security of Embodied AI
β24Updated 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
- β42Updated 4 months ago
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β51Updated 10 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussionsβ61Updated 8 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β53Updated last month
- Official repo of Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Roboticsβ23Updated last month
- Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safetyβ37Updated last month
- Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Generator, Generβ¦β17Updated 6 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β19Updated 6 months ago
- β38Updated 3 weeks ago
- β22Updated 7 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ33Updated last year
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β145Updated last month
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β28Updated 6 months ago
- Benchmarking Physical Risk Awareness of Foundation Model-based Embodied AI Agentsβ17Updated 4 months ago
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectorβ¦β24Updated 5 months ago
- official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Modelsβ58Updated 2 years ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β19Updated 6 months ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]β60Updated last year
- β44Updated 8 months ago
- β26Updated 2 weeks ago
- β51Updated 3 months ago
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"β28Updated last month
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdfβ20Updated last year
- Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks"β15Updated 4 months ago
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Modelsβ47Updated 4 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ190Updated 4 months ago
- [NeurIPS 2023] Content-based Unrestricted Adversarial Attackβ25Updated last year
- A collection of resources on attacks and defenses targeting text-to-image diffusion modelsβ65Updated last month
- Summaries of ICML 2024 papersβ10Updated 8 months ago
- β70Updated 9 months ago