arXiv · cs.AI · Bryan C. Boots · 8 小时前模型评分35
研究：网络化合成社会工程如何误导 人工智能（AI，Artificial Intelligence） 服务并削弱纠错效果
Networked Synthetic Social Engineering on the Web
导读
研究用 Qwen3-4B 在 Agent Service Exchange and Evidence Commons（ASE-EC）的 1,080 个研究单元上测试合成社会工程（服务器发送事件（SSE。
分类置信度
中 · 待人工复核
- 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
- “We examine these networked consequences of synthetic social engineering (SSE), deliberately misleading influence intended to redirect AI recipients from authorized objectives.”
- “We test four relationships using Qwen3-4B and two briefing tasks across 1,080 research units in our Agent Service Exchange and Evidence Commons (ASE-EC).”
- “Without scope revalidation, corrections identifying dependent reports reduced residual invalid decisions from 14.4% to 8.1% at equal notification coverage and increased successful report repairs from 16/63 to 36/63.”
- “Scope revalidation added no demonstrated protection, and clearing dialogue offered no established recovery advantage.”
- “Unapproved requests persisted, all blocked by an external gateway.”
来源：arXiv · cs.AI · arxiv.org