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
Attacker access
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 240papers have no tags yet and are not included in filtered results.
Another 240papers do not have category tags yet and are not included in filtered results.
- OtherarXiv 2609.08832
自进化智能体框架缩小 LLM 智能体的「一致性差距」
提出离线两阶段框架，诊断易翻转步骤并生成记忆指南以稳定智能体
- arXiv
- 2609.08832
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- GPT-4.1, GPT-OSS-120B
- ComponentMemory
Abstract用离线一致性诊断生成记忆指南，在 AppWorld 上提高重复全通过率。
作者要缩小的是 LLM 智能体平均通过、重复不稳之间的 consistency gap，即 Mean@k 减 Passˆk。
Salesforce AI Research 重测自改进 Agent
重测记忆型自改进 Agent 的运行方差与任务顺序敏感性
- arXiv
- 2608.18066
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- GPT-5-mini, Gemini-2.5-Pro, GPT-OSS-120B and others4
- ComponentMemory
Abstract论文揭示了基于记忆的自改进智能体在多次运行和乱序下的脆弱性，并指出规约不完备是诱发退化的关键瓶颈。
这篇论文是对基于文本记忆的自我改进智能体在复杂环境中评估可靠性的实证研究。
- AttacksarXiv 2607.25936
研究提出 RolePlay 框架：利用人设条件放大 LLM 推理成本
提出 RolePlay 框架，用人设条件放大 LLM 单次推理开销
- arXiv
- 2607.25936
- Published
- Layer
- Prompt layer
- Setting
- Models and APIs
- Attacker
- Black-box
- Evaluated models
- DeepSeek-V4-Pro, Gemini-3.5-Flash, Qwen-3.5-Plus and others5
- AttacksDenial of service
- TechniqueRole-play and persuasion
- ComponentReasoning chains
- AttacksarXiv 2606.14517
Researchers disclose a reasoning-amplified denial-of-service attack against LLM agent guardrails
提出针对 Agent 护栏的推理扩展拒绝服务攻击
- arXiv
- 2606.14517
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Attacker
- Black-box
- Evaluated models
- TS-Guard-8B, Qwen3.5-9B, DeepSeek-V3.2 and others11
- AttacksDenial of service
- TechniqueReasoning-chain manipulation
- ComponentGuardrails and judges
- AttacksarXiv 2605.30040
研究揭示 LLM 按 token 计费可被服务商系统性虚报
构造可通过计费审计的 token 虚报，使服务商系统性超收
- arXiv
- 2605.30040
- Published
- Layer
- Infrastructure layer
- Setting
- Models and APIs
- Evaluated models
- PALACE domain-adapted auditor
- AttacksDetection evasion
- TechniqueDefense-targeted
- ComponentMonitors
Abstract不诚实提供方可在三种 token 审计上虚报并通过检查，作者认为需改用提供方不控制的证据。
不透明 LLM 的按 token 计费里，现有审计核验的是提供方可控的证据，不诚实提供方可以虚报并通过检查。。
- AttacksarXiv 2605.13338
研究者提出层级遗传算法黑盒攻击，诱导推理模型过度思考
提出层级遗传算法 HGA，扰动题目逻辑结构诱发推理模型过度思考
- arXiv
- 2605.13338
- Published
- Layer
- Prompt layer
- Setting
- Models and APIs
- Attacker
- Black-box
- Evaluated models
- DeepSeek-R1 (671B), Qwen3-Thinking, GPT-o3 and others5
- AttacksDenial of service
- TechniqueAutomated search
- ComponentReasoning chains
AbstractHGA 在黑盒推理模型上用逻辑扰动拉长输出，作者称可从小代理迁移，查询成本是其局限。
You have reached the end