euanong / image-hijacksLinks
Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime
β50Updated 2 years ago
Alternatives and similar repositories for image-hijacks
Users that are interested in image-hijacks are comparing it to the libraries listed below
Sorting:
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Modelsβ238Updated last year
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β68Updated last year
- β50Updated last year
- β48Updated 9 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ171Updated 3 months ago
- β48Updated last year
- β101Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β28Updated 11 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β76Updated 8 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ212Updated 9 months ago
- Accepted by ECCV 2024β154Updated 11 months ago
- β62Updated 5 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β54Updated 8 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and furβ¦β75Updated 4 months ago
- β37Updated last year
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Modelsβ57Updated last year
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β166Updated 3 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"β83Updated last year
- A package that achieves 95%+ transfer attack success rate against GPT-4β23Updated 11 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β57Updated 6 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β36Updated 11 months ago
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignmentβ23Updated 3 months ago
- Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Modelsβ18Updated 11 months ago
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Modelsβ31Updated 3 months ago
- Accepted by IJCAI-24 Survey Trackβ215Updated last year
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Modelsβ30Updated 8 months ago
- Comprehensive Assessment of Trustworthiness in Multimodal Foundation Modelsβ22Updated 6 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ39Updated last year
- β35Updated 4 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β64Updated last year