会员服务
Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
Arxiv
0+阅读 · 11月7日
Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks
Arxiv
0+阅读 · 11月1日
DefenSee: Dissecting Threat from Sight and Text - A Multi-View Defensive Pipeline for Multi-modal Jailbreaks
Arxiv
0+阅读 · 12月1日
Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
Arxiv
0+阅读 · 11月3日
Immunity memory-based jailbreak detection: multi-agent adaptive guard for large language models
Arxiv
0+阅读 · 12月3日
Beyond Model Jailbreak: Systematic Dissection of the "Ten DeadlySins" in Embodied Intelligence
Arxiv
0+阅读 · 12月6日
VERA: Variational Inference Framework for Jailbreaking Large Language Models
Arxiv
0+阅读 · 11月6日
Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security
Arxiv
0+阅读 · 11月18日
A Practical Framework for Evaluating Medical AI Security: Reproducible Assessment of Jailbreaking and Privacy Vulnerabilities Across Clinical Specialties
Arxiv
0+阅读 · 12月9日
Chain-of-Lure: A Universal Jailbreak Attack Framework using Unconstrained Synthetic Narratives
Arxiv
0+阅读 · 11月13日
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
Arxiv
0+阅读 · 11月16日
Jailbreaking in the Haystack
Arxiv
0+阅读 · 11月5日
参考链接
微信扫码咨询专知VIP会员
Top