Translation in progress Some entries still include text in the original language.

Oct 13 · Tuesday

All papers

Found 16 papers

Filter5

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.

Attack type：Poisoning and backdoors Attack surface / entry point：Web pages and interfaces Attack surface / entry point：Images, audio and video Layer：Model layer Layer：Application layer Clear all

Another 201papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.11932Oct 8
A Fudan team measures the citation fragility of AI search: ordinary posts can enter citations and answer text
Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.
arXiv
2610.11932
Published
Oct 8
Layer
Application layer
Setting
LLM applications
Evaluated models
Grok, Doubao, ChatGPT and others10
- AttacksPoisoning and backdoors
- ComponentRAG
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.
Paper analysisRead analysis
DefensesarXiv 2610.00450Oct 1
ZoneClaw 用记忆分区防御 OpenClaw 式计算机使用 Agent 的持久记忆攻击
提出 ZoneClaw，用记忆分区防御计算机使用 Agent 的持久记忆攻击
arXiv
2610.00450
Published
Oct 1
Layer
Application layer
Setting
Browser and computer use
Evaluated models
Claude Sonnet 4.6, GPT-5.5, GLM-5.2 and others4
- DefensesInstruction–data separation
- AttacksPoisoning and backdoors
- ComponentMemory
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.35912Sep 28
MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作
提出 MMSkillRisk 基准，评测多模态技能图像中的隐藏指令诱导 Agent 越权操作
arXiv
2609.35912
Published
Sep 28
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6-sol, Kimi-K2.6, Kimi-K3 and others6
- AttacksPrompt injection
- TechniqueCross-modal payloads
- ComponentMCP and skills
Abstract论文提出 MMSkillRisk 基准与 NCVA 攻击，揭示多模态技能中教学图像潜藏指令可引发未授权操作并与良性任务共存。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.28915Sep 24
研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性
构建 ACE 语料，评测内核级证据对 Agent 攻击检测的有效性
arXiv
2609.28915
Published
Sep 24
Layer
Application layer
Setting
coding agent
Evaluated models
AdaBoost, XGBoost, TabPFN and others10
- AttacksPrompt injection
- ComponentMCP and skills
AbstractACE 用配对的内核与应用层证据表明，syscall 痕迹可判别智能体攻击，两层组合通常更好。
ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.19705Sep 17
SoK 论文提出 FARSIGHT 框架，评测 15 个学术金融 LLM 交易 Agent 的鲁棒性与安全失败
用 FARSIGHT 方案级评测金融 LLM 交易 Agent 的稳健性与安全失败
arXiv
2609.19705
Published
Sep 17
Layer
Application layer
Setting
AI Agent
Evaluated models
ChatGPT Deep Research
- AttacksPrompt injection
- RiskDangerous agent actions
- ComponentMemory
Paper analysisRead analysis
AttacksarXiv 2609.13889Sep 12
PMPA：针对 OpenClaw 与 Claude Code 的持久记忆投毒攻击
提出 PMPA，经外部源向 Agent 持久记忆投毒并跨会话泄露隐私
arXiv
2609.13889
Published
Sep 12
Layer
Application layer
Setting
coding agent
Evaluated models
DeepSeek-V4-Flash, DeepSeek-V4-Pro, Qwen3-Max
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract论文提出了持久记忆投毒攻击 PMPA，报告了 harness 智能体在处理外部数据时易受跨会话记忆投毒与隐私泄露的风险。
Paper analysisRead analysis
DefensesarXiv 2609.02127Sep 2
论文提出带类型溯源与断言护栏，防止持久化 AI Agent 把不可信输入当作自身历史
提出类型化溯源与断言护栏，约束持久 Agent 释放自传断言
arXiv
2609.02127
Published
Sep 2
Layer
Application layer
Setting
AI Agent
- DefensesWatermarking and provenance
- AttacksPoisoning and backdoors
- ComponentMemory
Paper analysisRead analysis
AttacksarXiv 2607.10712Jul 12
研究提出间接数据投毒攻击，可操纵 Claude、Codex 与 Gemini 的科研结论
提出间接数据投毒攻击，操纵科研智能体得出虚假结论
arXiv
2607.10712
Published
Jul 12
Layer
Application layer
Setting
science agent
Evaluated models
Claude Code with Claude Opus 4.7, Codex with GPT-5.5, Gemini CLI with Gemini 3.1 Pro
- DefensesInstruction–data separation
- AttacksPoisoning and backdoors
Paper analysisRead analysis
AttacksarXiv 2606.04329Jun 3
研究者系统研究 LLM 智能体记忆投毒攻击并提出 MPBench 基准
系统研究 LLM 智能体记忆投毒并构建基准 MPBench
arXiv
2606.04329
Published
Jun 3
Layer
Application layer
Setting
AI Agent
Evaluated models
Meta-Llama-3.1-70B-Instruct, Deberta-v3-base, Llama-3.1-8B-Instruct and others5
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract系统研究了智能体记忆投毒风险，揭示了写入渠道漏洞，构建了 MPBench 基准并指出提示注入防御的局限。
Paper analysisRead analysis
AttacksarXiv 2605.15338May 15
Hidden in Memory: Latent Memory Poisoning of LLM Agents
提出潜伏记忆投毒，诱导 Agent 把外部文档写成持久伪造记忆
arXiv
2605.15338
Published
May 15
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-5.4, GPT-5.5, Claude Sonnet 4.6 and others12
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract持久记忆成为跨会话攻击面：通用载荷可写入伪造记忆，并在相关后续任务中影响行为。
sleeper memory poisoning 研究带持久记忆的 LLM 助手：外部文档能否让助手存下一则伪造的用户记忆，并在原文档消失后的新会话里被取回、用来改变回复或动作。
Paper analysisRead analysis
AttacksarXiv 2604.02623Apr
论文提出 eTAMP 攻击：网页内容注入可跨会话污染 Web Agent 记忆
提出 eTAMP，用网页内容跨会话投毒 Web Agent 轨迹记忆并诱导越权操作
arXiv
2604.02623
Published
Apr
Layer
Application layer
Setting
web agent
Evaluated models
GPT-5-mini, GPT-5.2, GPT-OSS-120B and others6
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract论文提出了基于环境注入的跨任务记忆投毒攻击 eTAMP，作者报告智能体在环境压力下易感性增加且能力与安全并不协同。
该论文评估了基于大语言模型的 Web 智能体在利用历史交互轨迹进行记忆增强时的安全脆弱性。
Paper analysisRead analysis
DefensesarXiv 2603.12644Mar 13
Revealing security threats and defense architectures for autonomous agents: an OpenClaw case study
Reviews threats to autonomous agents and proposes a full-lifecycle defense blueprint, FASA
arXiv
2603.12644
Published
Mar 13
Layer
Application layer
Setting
AI Agent
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
AbstractUsing OpenClaw as an example, it divides risks into three layers and uses FASA to describe defense from input to system execution.
This is a threat review and defense architecture report using OpenClaw as a case study, not a scored attack or defense evaluation.
Paper analysisRead analysis
DefensesarXiv 2603.11619Mar 12
Taming OpenClaw: Security Analysis and Mitigation of Threats in Autonomous LLM Agents
Proposes a defense-in-depth aligned with the five stages to mitigate cross-stage threats to autonomous agents
arXiv
2603.11619
Published
Mar 12
Layer
Application layer
Setting
AI Agent
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentMCP and skills
AbstractThis is a lifecycle threat analysis and layered mitigation design for OpenClaw, with the cases serving as qualitative evidence.
This is a lifecycle threat analysis of OpenClaw, accompanied by a set of layered mitigation designs. The problem addressed is: when autonomous agents connect instant messaging, persistent memory, third-party plugins, and high-privilege execution, attacks are no longer limited to single-turn jailbreaks but can compound across multiple stages from initialization to execution. The authors argue that defenses hardening only individual interfaces cannot stop such cross-temporal attacks.
Paper analysisRead analysis
AttacksarXiv 2602.15654Feb 17
Zombie Agent: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injection
提出 Zombie Agent 攻击，经网页间接注入将载荷写入长期记忆并跨会话触发
arXiv
2602.15654
Published
Feb 17
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemini-2.5-Flash, GLM-4.7-Flash
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract记忆写入把一次网页间接注入变成跨会话控制。
Zombie Agent 把自进化 LLM 智能体的跨会话记忆当成攻击面：攻击者只发布网页，良性任务读入后，正常记忆更新留下载荷，并在以后无关会话里触发未授权工具行为。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2602.08412Feb 9
From Assistant to Double Agent: Formalizing and Benchmarking OpenClaw Attacks against Personalized Local AI Agents
提出 PASB，端到端评测 OpenClaw 的系统级攻击
arXiv
2602.08412
Published
Feb 9
Layer
Application layer
Setting
AI Agent
Evaluated models
Llama-3.1-70B-Instruct, Qwen2.5-7B-Instruct, GPT-4o-mini
- AttacksPrompt injection
- ComponentMemory
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2601.10923Jan 16
Hidden-in-Plain-Text: A benchmark for indirect prompt injection in social network RAG
用 OpenRAG-Soc 评测社交网页 RAG 的间接提示注入与检索投毒
arXiv
2601.10923
Published
Jan 16
Layer
Application layer
Setting
LLM applications
Evaluated models
Llama-3-8B-Instruct, Mistral-7B-Instruct, Qwen2.5-14B and others8
- AttacksPrompt injection
- TechniqueEncoding and obfuscation
- ComponentRAG
Paper analysisRead analysis

You have reached the end

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop

All papers

Attack type

Attack technique

Defense type

Impact

System type

Attack surface / entry point

Layer

System component

A Fudan team measures the citation fragility of AI search: ordinary posts can enter citations and answer text

ZoneClaw 用记忆分区防御 OpenClaw 式计算机使用 Agent 的持久记忆攻击

MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作

研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性

SoK 论文提出 FARSIGHT 框架，评测 15 个学术金融 LLM 交易 Agent 的鲁棒性与安全失败

PMPA：针对 OpenClaw 与 Claude Code 的持久记忆投毒攻击

论文提出带类型溯源与断言护栏，防止持久化 AI Agent 把不可信输入当作自身历史

研究提出间接数据投毒攻击，可操纵 Claude、Codex 与 Gemini 的科研结论

研究者系统研究 LLM 智能体记忆投毒攻击并提出 MPBench 基准

Hidden in Memory: Latent Memory Poisoning of LLM Agents

论文提出 eTAMP 攻击：网页内容注入可跨会话污染 Web Agent 记忆

Revealing security threats and defense architectures for autonomous agents: an OpenClaw case study

Taming OpenClaw: Security Analysis and Mitigation of Threats in Autonomous LLM Agents

Zombie Agent: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injection

From Assistant to Double Agent: Formalizing and Benchmarking OpenClaw Attacks against Personalized Local AI Agents

Hidden-in-Plain-Text: A benchmark for indirect prompt injection in social network RAG