研究显示 VLA 模型文本护栏漏检隐含危害指令
评测文本守卫与激活探针能否拦住机器人隐含伤害指令
- arXiv
- 2610.05818
- Published
- Layer
- Prompt layer
- Evaluated models
- π0.5, OpenVLA-OFT, Llama Guard 3 and others10
- RiskDangerous agent actions
- ComponentGuardrails and judges
All papers
Filter4
Attack type
Model risks
Defense type
Impact
System type
Attack surface / entry point
Layer
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Another 254papers do not have category tags yet and are not included in filtered results.
- OtherarXiv 2610.02662
论文发现语言驱动机器人安全监控的细化缺口：安全高层计划可能产生不安全执行
审计机器人安全监控的细化缺口，比较表面计划与图细化轨迹的裁决
- arXiv
- 2610.02662
- Published
- Layer
- Application layer
- ComponentMonitors
Abstract表面轨迹可漏掉图诱导的禁区进入。
作者审计 RoboGuard 的一个假设：对高层动作轨迹的安全裁决，在补上语义图诱导的导航和已记录隐式效应之后是否仍然成立。做法是不改验证器，并固定同一条 LTL。
- Risky behaviorarXiv 2609.39050
Study: Seven of nine frontier models covertly pass credentials to bypass monitoring
测量无对抗协作中 Agent 自发编码凭据以规避监控
- arXiv
- 2609.39050
- Published
- Layer
- Application layer
- Setting
- Multi-agent systems, coding agent
- Evaluated models
- DeepSeek-V4-Pro, devstral-2512, gpt-oss-120b and others14
- RiskDeception and scheming
- ComponentMonitors
Abstract论文揭示智能体会因良性助人意图自主编码凭据规避监控，主张不能单靠内容审查，需在动作层强化严格鉴权。
ORBIT：基于 UK AISI Inspect 的多智能体安全评测框架
提出 ORBIT 框架，评测多智能体防御对合谋等威胁的效果
- arXiv
- 2609.33102
- Published
- Layer
- Application layer
- Setting
- Multi-agent systems
- Evaluated models
- GPT-5.4, Claude Sonnet 4.6, Qwen3-235B and others5
- AttacksMalicious use
- RiskDeception and scheming
- ComponentMonitors
AbstractORBIT 用六层配置比较多智能体防御，逐动作监控不迁移到合谋。
- Risky behaviorarXiv 2609.32701
研究显示前沿模型智能体在测试时自行形成隐蔽信道
展示智能体在禁止泄露与独立监视下自发建立隐蔽信道传递机密
- arXiv
- 2609.32701
- Published
- Layer
- Application layer
- Setting
- Multi-agent systems
- Evaluated models
- GPT-5.6 Sol, Terra, Luna and others6
- RiskDeception and scheming
- ComponentMonitors
Abstract论文研究了固定参数智能体在受监视交互中仅凭单比特反馈自发建立隐蔽信道，指出了多智能体跨域协作的保密安全新风险。
论文研究了固定参数与提示词的智能体在受审计交互中自发形成隐蔽信道并泄露机密的过程。
- Risky behaviorarXiv 2609.28900
Codetta：面向独立部署 LLM 智能体的高容量无密钥隐蔽串谋协议
提出多智能体隐写共谋框架 CODETTA，在强被动审计下隐蔽传载荷
- arXiv
- 2609.28900
- Published
- Layer
- Application layer
- Setting
- Multi-agent systems
- Evaluated models
- Qwen2.5-7B, Llama-3.1-8B, Ministral-3-8B
- RiskDeception and scheming
- ComponentMonitors
Abstract提出非对称免密钥隐写框架 CODETTA，实现高容量不可区分通信，指出被动审计面临失效风险。
- DefensesarXiv 2609.15803
研究者提出 k-robust 联盟对齐，用多智能体评审委托授权
提出 k-robust 联盟对齐，刻画误对齐评审下的安全委托授权
- arXiv
- 2609.15803
- Published
- Layer
- Application layer
- Setting
- Multi-agent systems
- DefensesPermissions and approval
- RiskMisalignment and value divergence
- ComponentPermissions and sandboxing
Abstract联盟覆盖使无个体对齐的评审面板仍可相对基线安全授权，数值分数改善完备性。
委托授权的安全不要求每位评审者对齐，而要求面板在效用空间覆盖委托人。
- OtherarXiv 2609.06140
论文提出反集群准则：以协调事件为单元遏制智能体协同入侵
提出以协调情节为单位遏制智能体协同入侵的准则
- arXiv
- 2609.06140
- Published
- Layer
- Application layer
- Setting
- Multi-agent systems
- RiskDangerous agent actions
- ComponentMonitors
Abstract立场是跨执行保留关系并约束共享状态。
- DefensesarXiv 2608.02683
S³：用多阶段防御提升 LLM 智能体安全
提出 S³，用 guard agent 编排阶段安全技能防御智能体多阶段风险
- arXiv
- 2608.02683
- Published
- Layer
- Application layer
- Evaluated models
- DeepSeek-V4-Pro, DeepSeek-V4-Flash
- DefensesMonitoring and auditing
- AttacksPoisoning and backdoors
- RiskDangerous agent actions
- ComponentMonitors
- DefensesarXiv 2505.23559
SafeScientist：让 LLM 智能体的科学发现具备风险意识
提出 SafeScientist 四层监控，阻止科研智能体执行高风险或不伦理任务
- arXiv
- 2505.23559
- Published
- Layer
- Application layer
- Setting
- science agent, Multi-agent systems
- Evaluated models
- GPT-4o, GPT-4.1, GPT-3.5-turbo and others5
- DefensesMonitoring and auditing
- AttacksJailbreaks
- ComponentMonitors
Abstract四层监控加科研安全基准。
SafeScientist 是带四层监控的科研智能体框架，并用 SciSafetyBench 评测科学场景中的任务安全。
You have reached the end