按年被提到
20262026 · 2 次2026
AI 安全、伦理与社会影响›智能体安全与滥用·arXiv:2601.09923 · cs.AI

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents

Hanna Foerster, Tom Blanchard, Kristina Nikolić, Ilia Shumailov, Cheng Zhang, Robert Mullins, Nicolas Papernot, Florian Tramèr, Yiren Zhao · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-01-16 · 最近 2026-09-28
2不同的人
2活跃月份
2讨论串
4被引(OpenAlex)
arXiv 摘要(候选层不写导读)

AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior. Among proposed defenses, architectural isolation provides the strongest guarantees by strictly separating trusted task planning from untrusted environment observations. However, applying this design to Computer Use Agents (CUAs), which automate tasks by viewing screens and executing actions, presents a fundamental challenge. Current agents require continuous observation of UI state to determine each action, which conflicts with the isolation required for security. We resolve this tension by demonstrating that UI workflows, while dynamic, are structurally predictable. Single-shot planning, where a trusted planner emits upfront a complete branching plan covering all anticipated runtime states, provides control flow integrity guarantees against arbitrary instruction injections. We introduce NOVA (Navigating via Observation, Verification, and Action) to make this viable in the combinatorially large UI state space, where the plan can invoke a perception model to resolve runtime values such as UI coordinates. We evaluate our design on OSWorld, and retain up to 57% of the performance of frontier models while improving performance for smaller open-source models by up to 19%, demonstrating that rigorous security and utility can coexist in CUAs. Although upfront planning prevents instruction injections, we show that additional measures are needed to defend against \textbf{Branch Steering} attacks, where adversaries deceive the perception model into routing execution down attacker-preferred branches of the plan, such as redirecting the agent to a malicious website.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论troelsSteegin · 2026-09

“CaMeL, from "Defeating Prompt Injections by Design", https://arxiv.org/abs/2503.18813 See also "CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents", https://arxiv.org/abs/2601.09923v1”

What would a serious AI product look like?原评论 ↗
被提交为 story · 1 次