会员服务
Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs
Arxiv
0+阅读 · 3月14日
Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads
Arxiv
0+阅读 · 3月13日
Ignore All Previous Instructions: Jailbreaking as a de-escalatory peace building practise to resist LLM social media bots
Arxiv
0+阅读 · 3月2日
A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
Arxiv
0+阅读 · 2月24日
PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
Arxiv
0+阅读 · 2月25日
Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
Arxiv
0+阅读 · 2月20日
JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models
Arxiv
0+阅读 · 2月28日
Untargeted Jailbreak Attack
Arxiv
0+阅读 · 3月2日
Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models
Arxiv
0+阅读 · 3月11日
MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs
Arxiv
0+阅读 · 2月28日
VII: Visual Instruction Injection for Jailbreaking Image-to-Video Generation Models
Arxiv
0+阅读 · 2月24日
When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
Arxiv
0+阅读 · 3月4日
Towards Realistic Guarantees: A Probabilistic Certificate for SmoothLLM
Arxiv
0+阅读 · 2月20日
PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs
Arxiv
0+阅读 · 3月7日
SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge
Arxiv
0+阅读 · 3月6日
参考链接
微信扫码咨询专知VIP会员
Top