揭穿LLM数据隐私漏洞：通过训练数据投毒定向提取未见样本，AI安全新威胁。
arXiv:2606.17110v1 Announce Type: cross Abstract: Large Language Models are increasingly trained on proprietary or sensitive data, from private health…
大模型后训练阶段面临全新威胁：顺序数据投毒攻击，揭示安全漏洞与防御方法。
arXiv:2606.04929v1 Announce Type: new Abstract: LLM post-training proceeds through multiple stages, e.g., supervised fine-tuning (SFT) followed by rei…
教你用数据投毒对抗AI：让模型失效的实战策略与工具解析
Article URL: https://www.youtube.com/watch?v=Z8aLGHmnRyc Comments URL: https://news.ycombinator.com/item?id=48321906 Points: 2 # Comments: 0
全新后门攻击方法，通过微调数据投毒实现隐蔽控制大语言模型，USENIX Security '26论文。
arXiv:2605.26595v1 Announce Type: cross Abstract: Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can po…
顶会论文新发现：用LLM重写对抗数据投毒，一种温和却有效的后门攻击防御策略。
arXiv:2605.19147v1 Announce Type: cross Abstract: Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samp…