提出通过提示注入对LLM进行指纹识别，破解模型衍生关系判断难题，为AI安全溯源提供新思路。
arXiv:2509.25448v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are often modified after release through post-processing such a…
无需账户和API密钥，一键部署本地防火墙，实时拦截AI代理的提示注入攻击，保护数据安全。
I got really tired of giving artificial intelligence agents access to tools. Then I had no idea what they were actually doing. So I created Korveo. Ko…
MIT 6.566客座讲座，深入解析AI Agent安全风险与防御，含演示代码和前沿论文。
Article URL: https://github.com/anishathalye/ai-agent-security-lecture Comments URL: https://news.ycombinator.com/item?id=48181324 Points: 3 # Comment…
OpenAI深度解析提示注入攻击：前沿AI安全挑战与防御策略
Prompt injections are a frontier security challenge for AI systems. Learn how these attacks work and how OpenAI is advancing research, training models…
提示过滤为何总是失败？因为问错了问题；真正的威胁模型是什么？给出替代思路。
Every prompt injection defense I’ve seen makes the same mistake. It asks the wrong question. The wrong question: “Does this prompt contain dangerous w…
AI agent的安全防线不是加固模型，而是假设攻击者已完全控制提示。工具权限必须与调用者绑定，否则一次注入就能让数据越界。当数据来源不可信时，间接注入比直接攻击更危险。
An AI agent is a language model with a system prompt and a set of tools. Tools extend the model's capabilities by adding access to APIs, file systems,…