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
β68Updated 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¦β28Updated 10 months ago
- Accepted by ECCV 2024β152Updated 11 months ago
- β47Updated 9 months ago
- β48Updated last year
- β61Updated 5 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ171Updated 2 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β76Updated 8 months ago
- β50Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β35Updated 11 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
- Code for ICCV2025 paperββIDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselvesβ14Updated 2 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β54Updated 8 months ago
- β101Updated last year
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Modelsβ225Updated 2 weeks ago
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safetyβ49Updated 2 months ago
- β37Updated last year
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignmentβ23Updated 3 months ago
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreβ¦β39Updated 2 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β64Updated last year
- Code for the paper "Jailbreak Large Vision-Language Models Through Multi-Modal Linkage"β16Updated 9 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ212Updated 8 months ago
- β35Updated 4 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
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Modelsβ237Updated last year
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtimeβ50Updated 2 years ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β166Updated 2 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ39Updated last year
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuningβ10Updated 10 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Modelsβ30Updated 8 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β23Updated 10 months ago