ASTRAL-Group / ASTRA
Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks"
β11Updated 4 months ago
Alternatives and similar repositories for ASTRA:
Users that are interested in ASTRA are comparing it to the libraries listed below
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β45Updated 9 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β17Updated 5 months ago
- β36Updated 9 months ago
- β40Updated 3 months ago
- β32Updated 4 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β18Updated 5 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ127Updated last month
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and furβ¦β52Updated 8 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β44Updated 2 months ago
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacksβ16Updated last week
- β43Updated 7 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β28Updated 5 months ago
- β45Updated 3 months ago
- β20Updated 6 months ago
- An implementation for MLLM oversensitivity evaluationβ13Updated 4 months ago
- β19Updated last month
- β31Updated 8 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ32Updated last year
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"β24Updated last year
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)β23Updated this week
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β50Updated last week
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794β¦β19Updated 8 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Modelsβ53Updated 11 months ago
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectorβ¦β24Updated 4 months ago
- Accepted by ECCV 2024β117Updated 5 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdfβ19Updated last year
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignmentβ10Updated 3 weeks ago
- Comprehensive Assessment of Trustworthiness in Multimodal Foundation Modelsβ16Updated 2 weeks ago
- Benchmarking Physical Risk Awareness of Foundation Model-based Embodied AI Agentsβ17Updated 4 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Modelsβ23Updated 3 months ago