arXiv · cs.AI · Minjae Seo, Wonwoo Choi, Geonwoo Han, Taekyoung Kwon, Yongsu Kim, Sang Seo, Jaewon Noh, Hankyul Baek, Seongyun Seo, Myoungsung You · 5 小时前模型评分72
SBIA 研究：借社交媒体评论与技能向个人 人工智能（AI，Artificial Intelligence） 智能体记忆注入间接偏见
MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Content
导读
研究者提出 SBIA（Stealthy Bias Injection Attack，隐蔽偏见注入攻击），在热门社交媒体帖子下发布经过伪装和水印的评论，再分发一个摘要技能，让智能体自己把这些评论写入持久记忆。
分类置信度
中 · 待人工复核
- 存在未解决的相邻类别：governance-services，需要人工复核。
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “Leveraging this curation path, we present SBIA, a Stealthy Bias Injection Attack that introduces adversarial bias through ordinary external content while relying on the agent itself to perform the memory write.”
- “On BiasBench with 7,000 crafted SNS comments and seven LLMs on OpenClaw, SBIA achieves attack success rates of at least 96% across models and even 91% on GPT-5.5 in four downstream tasks.”
- “Despite this effectiveness, its skill passes all eight evaluated malicious-skill scanners and ClawHub's official skill scanning pipeline.”
- “We further propose a memory boundary defense that detects 82.1% of injected entries at a 5.6% FPR.”
来源：arXiv · cs.AI · arxiv.org