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
Filter3
Impact
System type
System component
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 262papers have no tags yet and are not included in filtered results.
Another 262papers 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。
- 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
You have reached the end