huanranchen / VLMTransfer
A package that achieves 95%+ transfer attack success rate against GPT-4
β17Updated 5 months ago
Alternatives and similar repositories for VLMTransfer:
Users that are interested in VLMTransfer are comparing it to the libraries listed below
- β40Updated 3 months ago
- β36Updated 9 months ago
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β45Updated 9 months ago
- β32Updated 3 months ago
- β43Updated 7 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ32Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β18Updated 5 months ago
- β19Updated 6 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β44Updated 2 months ago
- β31Updated 8 months ago
- β45Updated 3 months ago
- Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Modelsβ13Updated 5 months ago
- Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Generator, Generβ¦β15Updated 5 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Modelsβ51Updated 11 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β61Updated 2 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
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"β78Updated last year
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)β14Updated 5 months ago
- Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?β21Updated last month
- Accepted by ECCV 2024β115Updated 5 months ago
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtimeβ44Updated last year
- Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks"β11Updated 4 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdfβ19Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLMβs Safety without Hurting Performance"β35Updated 11 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and furβ¦β51Updated 8 months ago
- β93Updated last year
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignmentβ10Updated 2 weeks ago
- β19Updated 11 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β54Updated 8 months ago
- Comprehensive Assessment of Trustworthiness in Multimodal Foundation Modelsβ15Updated last week