Another 213papers do not have category tags yet and are not included in filtered results.
Propose X-AgentRed, which uses a tool dependency graph to red-team cross-service unauthorized harm in personal agents
Proposes DREAM, which selectively weakens agent-poisoned memories while preserving benign memories.
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
AbstractThe authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.
AbstractThe authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.
Retest and extend prompt injection against AI agents, and use Agent Card deception to manipulate A2A selection
The authors retested prompt injection on their own LangChain, AutoGen, and A2A systems, and modified the Agent Card to see if choices shifted. The abstract states the experiments mainly highlight single-agent weaknesses while extending attacks to multi-agent.
提出 BRANCH 方法，用分支搜索绕过多扫描器护栏
提出 OPUR 攻击，用似然梯度优化对抗后缀越狱 LLM 智能体
提出 AgentTracer，事后定位间接提示注入的注入点并重建攻击链
提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链
这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。
提出 Secure-CUA，用动作事务约束计算机使用智能体的不可信影响
Secure-CUA 要限制图形界面里不可信内容对 CUA 决策和 GUI 执行的影响，同时保留合法任务所需的不可信信息。
提出 PackHallu，经规则文件提示注入诱导编码 Agent 换用攻击者指定包
PackHallu 研究一种针对编程智能体规则文件的提示注入：让智能体在本应使用合法依赖时，改导入攻击者指定并控制的包。
提出 WebMirage，用局部对抗图像劫持视觉网页 Agent 的浏览器操作
WebMirage 是一个面向视觉定位网络智能体的流水线感知端到端红队攻击框架。
提出 SPECGUARD，用 Lean 证书在编码 Agent 执行前证明任务冲突
Abstract提出预执行冲突检测与证明框架，在多个基准和真实仓库中成功证明任务与测试不可同时满足。
提出 ASPIRE 行为图搜索，开放式发现 Agent 提示注入漏洞
ASPIRE 是给搭建方用的智能体提示注入红队引擎，目标是开放式画出可利用的行为路径，而不是在固定任务上打磨一条载荷。
提出 AdvSim2Real，协同训练网页智能体抵御页面注入
提出 CredLeak-Bench，评测 Agent 面对钓鱼的凭据泄露与恢复
实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击
DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。
提出 SkillPoison，用局部有效的成功经验诱导自进化 Agent 形成过度泛化技能
SkillPoison 提出了一种针对自进化智能体经验到技能形成过程的攻击范式，通过组织已验证的成功经验诱导技能过度泛化。
评测编码智能体 harness 安全机制在对抗任务中的防护效果