erfanshayegani / Jailbreak-In-PiecesLinks
[ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
β67Updated last year
Alternatives and similar repositories for Jailbreak-In-Pieces
Users that are interested in Jailbreak-In-Pieces are comparing it to the libraries listed below
Sorting:
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β27Updated 10 months ago
- β46Updated 8 months ago
- β50Updated last year
- β47Updated last year
- Accepted by ECCV 2024β149Updated 10 months ago
- β58Updated 5 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β57Updated 5 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ164Updated 2 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β34Updated 10 months ago
- β37Updated last year
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ38Updated last year
- Code for the paper "Jailbreak Large Vision-Language Models Through Multi-Modal Linkage"β15Updated 8 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β74Updated 7 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β23Updated 10 months ago
- β102Updated last year
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreβ¦β35Updated last month
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β53Updated 7 months ago
- Code for ICCV2025 paperββIDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselvesβ11Updated last month
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and furβ¦β73Updated 3 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β162Updated 2 months ago
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Modelsβ216Updated 2 weeks ago
- β30Updated 3 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ209Updated 8 months ago
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignmentβ22Updated 2 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Modelsβ30Updated 8 months ago
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safetyβ48Updated last month
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIPβ24Updated 2 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β63Updated last year
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtimeβ50Updated last year
- Accepted by IJCAI-24 Survey Trackβ211Updated last year