研究测量 LLM Agent 记忆投毒防御的良性场景开销
测量记忆投毒防御在良性对话上的效用与 token 开销
- arXiv
- 2609.22818
- Published
- Layer
- Application layer
- Setting
- AI Agent
- AttacksPoisoning and backdoors
- ComponentMemory
Abstract写时代价落在噪声内。
在没有攻击的对话上，给记忆投毒防御计价，而不是再测一轮攻击是否被挡住。
All papers
Filter4
Attack type
Impact
System type
Attack surface / entry point
Layer
System component
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
Another 255papers do not have category tags yet and are not included in filtered results.
- AttacksarXiv 2608.21929
SkillBloat：通过技能注入对编码 Agent 发起 token 放大攻击
提出 SKILLBLOAT，改写技能文档放大编码 Agent token 消耗
- arXiv
- 2608.21929
- Published
- Layer
- Application layer
- Setting
- coding agent
- Evaluated models
- GLM-4.7-Flash, GLM-5, GPT-5.4 Mini and others4
- AttacksDenial of service
- TechniqueAutomated search
- ComponentMCP and skills
- AttacksarXiv 2608.12273
研究者提出 Convergent Detour Hijacking 攻击，可让技能型 LLM Agent 绕路并放大资源消耗
提出 CDH 攻击，让技能型 Agent 绕路放大资源消耗
- arXiv
- 2608.12273
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Claude-Haiku-4.5, DeepSeek-V4-Pro, DeepSeek-V4-Flash and others6
- AttacksPrompt injection
- TechniqueSelection manipulation
- ComponentMCP and skills
AbstractCDH 让静态技能在保持任务完成时拉高调用与 token，耗时则因后端而异。
CDH 是针对渐进披露技能智能体的发布者侧、纯文本攻击：一个静态协调器把本可正确完成的任务，拐进有界但更耗资源的技能绕路，再交还原任务。
- AttacksarXiv 2603.00902
Clawdrain: covertly draining tokens in OpenClaw Agents via tool call chains
提出 Clawdrain，用木马 skill 放大 OpenClaw 的 token 消耗
- arXiv
- 2603.00902
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Gemini 2.5 Pro
- AttacksDenial of service
- ComponentMCP and skills
- AttacksarXiv 2602.07379
Aegis: Governance, Integrity, and Security for AI Voice Agents
提出 Aegis 红队框架，多轮攻击高风险语音 Agent
- arXiv
- 2602.07379
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- GPT-4o, GPT-4o-mini, Gemini-1.5 Pro and others7
- AttacksDenial of service
- TechniqueMulti-turn escalation
- ComponentAudio
AbstractAegis red-teams three types of voice agents: query-based access eliminates authentication and leakage successes, but behavioral attacks remain.
Aegis uses multi-turn red-teaming evaluation on ALLM voice agents already integrated into business systems. The authors call this the first systematic red-teaming framework in this setting.
You have reached the end