liuxuannan / Awesome-Multimodal-JailbreakLinks
A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models
β231Updated last month
Alternatives and similar repositories for Awesome-Multimodal-Jailbreak
Users that are interested in Awesome-Multimodal-Jailbreak are comparing it to the libraries listed below
Sorting:
- π up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.β393Updated last week
- Accepted by IJCAI-24 Survey Trackβ216Updated last year
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ173Updated 3 months ago
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β71Updated last year
- β65Updated 4 months ago
- Accepted by ECCV 2024β158Updated 11 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β166Updated 3 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion modelsβ73Updated 6 months ago
- β48Updated last year
- 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¦β29Updated 11 months ago
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreβ¦β41Updated 3 months ago
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Modelsβ240Updated last year
- β51Updated 10 months ago
- Safety at Scale: A Comprehensive Survey of Large Model Safetyβ194Updated 7 months ago
- β101Updated last year
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Modelsβ30Updated 9 months ago
- Code for ICCV2025 paperββIDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselvesβ14Updated 2 months ago
- β52Updated last year
- β63Updated 6 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ213Updated 9 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and furβ¦β77Updated 5 months ago
- A list of recent papers about adversarial learningβ216Updated last week
- β20Updated 11 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β23Updated 11 months ago
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIPβ30Updated 3 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussionsβ64Updated last year
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ41Updated last year
- β35Updated 4 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β55Updated 8 months ago