liuxuannan / Awesome-Multimodal-JailbreakLinks
A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models
β220Updated 2 weeks ago
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.β383Updated 2 weeks ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ170Updated 2 months ago
- Accepted by IJCAI-24 Survey Trackβ214Updated 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
- Accepted by ECCV 2024β151Updated 11 months ago
- β62Updated 3 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion modelsβ74Updated 5 months ago
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Modelsβ236Updated last year
- Safety at Scale: A Comprehensive Survey of Large Model Safetyβ191Updated 7 months ago
- β48Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β28Updated 10 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β166Updated 2 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β53Updated 8 months ago
- β101Updated last year
- A list of recent papers about adversarial learningβ212Updated this week
- 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 ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Modelsβ30Updated 8 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ212Updated 8 months ago
- β61Updated 5 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β23Updated 10 months ago
- β50Updated last year
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreβ¦β39Updated 2 months ago
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)β62Updated this week
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and furβ¦β74Updated 4 months ago
- β47Updated 9 months ago
- Code for ICCV2025 paperββIDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselvesβ14Updated 2 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussionsβ64Updated last year
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsβ¦β81Updated 6 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ39Updated last year
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Modelsβ32Updated 3 months ago