mbzuai-nlp / AudioJailbreakLinks
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
☆27Updated 3 months ago
Alternatives and similar repositories for AudioJailbreak
Users that are interested in AudioJailbreak are comparing it to the libraries listed below
Sorting:
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆19Updated last year
- ☆26Updated last year
- ☆68Updated 9 months ago
- Official code implementation of SKU, Accepted by ACL 2024 Findings☆20Updated last year
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆117Updated last year
- ☆21Updated 2 months ago
- ☆53Updated 7 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆91Updated 8 months ago
- The official repository for guided jailbreak benchmark☆28Updated 5 months ago
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆55Updated 2 years ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆73Updated 7 months ago
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆122Updated 10 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆66Updated last year
- ☆13Updated 5 months ago
- ☆18Updated 9 months ago
- SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types☆23Updated last year
- [COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model☆23Updated last month
- ☆25Updated 9 months ago
- Code for Voice Jailbreak Attacks Against GPT-4o.☆36Updated last year
- Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"☆16Updated 10 months ago
- Data and code for the paper: Finding Safety Neurons in Large Language Models☆18Updated last year
- Panda Guard is designed for researching jailbreak attacks, defenses, and evaluation algorithms for large language models (LLMs).☆57Updated 2 months ago
- ☆45Updated 2 months ago
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆57Updated 4 months ago
- This repository contains the source code, datasets, and scripts for the paper "GenderCARE: A Comprehensive Framework for Assessing and Re…☆27Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆37Updated last year
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆37Updated 3 months ago
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)☆81Updated last week
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆32Updated last year
- Code and data for paper "Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?". (ACL 2025 Main)☆20Updated 6 months ago