对话多模态模型安全新漏洞：通过伪造助手消息实现越狱攻击，揭示未被探索的攻击面。
arXiv:2507.04673v2 Announce Type: replace Abstract: The rise of conversational interfaces has greatly enhanced LLM usability by leveraging dialogue hi…
多轮对话破解LLM防线，分解信用分配实现高效越狱攻击，揭示AI安全新漏洞
arXiv:2607.11070v1 Announce Type: new Abstract: Modern large language models (LLMs) operate in interactive multi-turn settings, making multi-turn jail…
用内部归因图揭示LLM越狱的运作机制，为AI安全提供新的可解释性视角。
arXiv:2607.07903v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit remarkable capabilities but remain highly vulnerable to adversa…
基于论文提出的工作流级越狱方法，检测IDE编码代理在任务分解、文件生成等环节的安全漏洞，适合安全研究者评估AI助手
arXiv:2607.03968v1 Announce Type: cross Abstract: Large language models are increasingly deployed as IDE-integrated coding agents that decompose tasks…
提出动态预算分配方法，高效评估多轮对话中LLM的越狱风险，解决计算瓶颈与稀有事件检测难题。
arXiv:2605.06605v2 Announce Type: replace Abstract: Evaluating and predicting the performance of large language models (LLMs) in multi-turn conversati…
最新研究发现，通过模拟审核轨迹可绕过函数调用LLM的安全限制，揭示大模型越狱攻击新路径。
arXiv:2607.00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). W…
一键破解语音模型？新研究系统优化多模态越狱攻击，直指spoken language model安全漏洞。
arXiv:2603.19127v2 Announce Type: replace Abstract: As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vul…
稀疏自编码器新应用：高效防御LLM越狱攻击，来自ICML可解释性研讨会的前沿研究。
arXiv:2602.12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety. We propose Cont…
在token生成前用位掩码策略拦截越狱攻击，reskSecure实现LLM安全防火墙新思路。
Links: PyPI: https://pypi.org/project/resksecure GitHub: https://github.com/Resk-Security/reskSecure Web: https://resk.fr Most prompt injection and ja…
发现LLM服务新漏洞：利用特殊Token操纵可越狱在线大模型，揭秘攻击原理与防范思路。
arXiv:2510.10271v2 Announce Type: replace-cross Abstract: Unlike regular tokens derived from existing text corpora, special tokens are artificially cr…
在AI聊天窗口内直接启动小型操作系统，无需离开对话即可制作应用，创意十足
Article URL: https://hollingsworthd.github.io/RAu/ Comments URL: https://news.ycombinator.com/item?id=48694257 Points: 1 # Comments: 0
利用中间层熵的动态变化检测大模型越狱，为AI安全提供新思路。
arXiv:2606.25182v1 Announce Type: cross Abstract: Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted p…
苹果A12/A13芯片现不可修补硬件漏洞，旧款iPhone越狱大门重开。
European offensive cybersecurity company Paradigm Shift released details of a flaw and a technique to exploit it that opens the door for hackers to un…
自动化攻击技术直击大模型多道防线，AI安全攻防再升级。
arXiv:2606.16751v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks.…
黑盒环境下的AI越狱防御新方法，利用结构验证与语义审计双重机制提升安全性
arXiv:2606.16527v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in user-facing systems, black-box jailbrea…
用遗传算法自动搜索黑盒大模型的越狱后缀，突破安全护栏的新攻击方法，副作用值得警惕。
arXiv:2606.15788v1 Announce Type: cross Abstract: Large Language Models (LLMs) constitute pivotal components within the AI-dominated information techn…
最新研究从理论上证明，任何通用防护措施都无法完全阻止大模型越狱攻击，揭示了LLM安全的根本困境
Article URL: https://github.com/brandoncarl/llm-jailbreaking/blob/main/On%20the%20Impossibility%20of%20Perfect%20Universal%20Guardians%20Against%20LLM…
Anthropic的安全警告意外引发政府叫停最强AI模型Fable 5，仅凭口头越狱证据凸显AI监管争议。
Anthropic isn't hiding its frustration. "We disagree that the finding of a narrow potential jailbreak should be cause for recalling a commercial model…
跨语言越狱检测新突破：不依赖语言特征，学习意图表示，有效识别多种语言下的越狱攻击。
arXiv:2606.11202v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in applications for global multilingual users, …
研究发现利用语法约束解码可诱导LLM生成恶意代码，揭示新型安全漏洞。
arXiv:2606.11817v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they m…