ASTRAL-Group / ASTRALinks
[CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks"
β35Updated last month
Alternatives and similar repositories for ASTRA
Users that are interested in ASTRA are comparing it to the libraries listed below
Sorting:
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β65Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β26Updated 9 months ago
- Accepted by ECCV 2024β147Updated 9 months ago
- β49Updated last year
- β46Updated 8 months ago
- β55Updated 4 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β23Updated 9 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ160Updated last month
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β51Updated 6 months ago
- β49Updated 11 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Modelsβ29Updated 7 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)β29Updated 9 months ago
- β31Updated 2 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β56Updated 4 months ago
- [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"β24Updated 2 weeks ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Modelsβ55Updated last year
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ209Updated 7 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β34Updated 9 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β73Updated 6 months ago
- β102Updated last year
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ37Updated last year
- An implementation for MLLM oversensitivity evaluationβ13Updated 8 months ago
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignmentβ22Updated last month
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β62Updated last year
- [ICCV-2025] Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Geneβ¦β23Updated 3 weeks ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and furβ¦β75Updated 3 months ago
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Modelsβ215Updated last month
- β37Updated last year
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β158Updated last month
- [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacksβ13Updated last year