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

Oct 12 · Monday

All papers

Found 22 papers

Filter4

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers 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：Code repositories and dependencies Attack surface / entry point：Inter-agent messages Clear all

Another 232papers 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
AttacksarXiv 2610.09264Oct 7
研究者提出 PackHallu：经规则文件提示注入对编码 Agent 发起包幻觉攻击
提出 PackHallu，经规则文件提示注入诱导编码 Agent 换用攻击者指定包
arXiv
2610.09264
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
Qwen2.5-Coder-7B, Qwen3-Coder-30B, Devstral-Small-2-24B and others19
- AttacksPrompt injection
- TechniqueAutomated search
AbstractPackHallu 诱导规则文件换包。
PackHallu 研究一种针对编程智能体规则文件的提示注入：让智能体在本应使用合法依赖时，改导入攻击者指定并控制的包。
Paper analysisRead analysis
AttacksarXiv 2610.07510Oct 6
PersistBD: attackers can strengthen backdoors before release so that they maintain high attack success rates even after developer SFT and RL.
提出 PERSISTBD，发布前强化供应链后门使其经良性 SFT 与 RL 后仍外发凭据
arXiv
2610.07510
Published
Oct 6
Layer
Application layer
Setting
coding agent
Evaluated models
Qwen2.5-Coder-3B-Instruct, Qwen2.5-Coder-7B-Instruct, Qwen3-Coder-30B-A3B-Instruct
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract总结了论文关于后门在 SFT/RL 中存活的发现、两因子机制、PERSISTBD 方法与核心数字。
本文研究第三方 LLM 智能体在开发者进行良性监督微调（SFT）和强化学习（RL）后训练时的后门持久性风险。
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
AttacksarXiv 2610.00430Oct 1
Memetic Trojans：利用社交传染在 LLM Agent 网络中传播对抗载荷
提出 memetic trojans，借助社交传染在 Agent 网络中传播对抗载荷
arXiv
2610.00430
Published
Oct 1
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
gpt-oss-120B, deepseek-v4.1-flash, qwen-32B and others5
- AttacksPoisoning and backdoors
- ComponentMCP and skills
Abstractmemetic trojans 用内生社会传染携带载荷。
Memetic trojans 是一类网络介导攻击：对抗载荷搭在智能体本来就会转发和点赞的内容上扩散，转发者不必被攻陷，也不必执行“请继续复制”的指令。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.32635Sep 26
TrustFork：显示身份如何劫持 LLM 智能体编排的权限
提出 TRUSTFORK 基准，评测展示身份劫持多智能体编排权限
arXiv
2609.32635
Published
Sep 26
Layer
Application layer
Setting
Multi-agent systems, coding agent
Evaluated models
GPT-5.6-Sol, GPT-5.6-Luna, Kimi-K3 and others8
- AttacksPrompt injection
Abstract论文提出了多智能体安全基准 TRUSTFORK，揭示展示身份如何劫持操作权威，并证明事后验证无法弥补已发生的执行破坏。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.32616Sep 26
Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作
提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作
arXiv
2609.32616
Published
Sep 26
Layer
Application layer
Setting
coding agent
Evaluated models
Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14
- AttacksPrompt injection
- RiskDangerous agent actions
Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。
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 2609.02774Sep 3
CodePoisonRAG：针对检索增强代码生成的知识投毒攻击
提出 CodePoisonRAG，对检索增强代码生成的知识库投毒以植入漏洞
arXiv
2609.02774
Published
Sep 3
Layer
Application layer
Setting
LLM applications
Evaluated models
Qwen 3.5 9B, Code Llama 13B, DeepSeek-Coder-V2 16B
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentRAG
AbstractCodePoisonRAG 展示了 RACG 外部知识库的新攻击面，在较低投毒率下可定向诱发指定漏洞并部分抵御防御。
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 2609.01222Sep 1
Researchers propose context privilege escalation attack, affecting 12 agent frameworks
提出针对 Agent Harness 的上下文特权提升攻击
arXiv
2609.01222
Published
Sep 1
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.5, GPT-5.4 mini, Claude-Sonnet-4.6 and others7
- AttacksPrompt injection
- TechniqueDormant triggers
- ComponentMemory
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.03272Aug 4
多智能体协同过滤系统的连接性攻击与防御研究
复现 AgentCF 上的多智能体攻防并刻画连通性作用
arXiv
2608.03272
Published
Aug 4
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Qwen3-235B-A22B, Claude Haiku 4.5, Mixtral 8×7B and others4
- AttacksPoisoning and backdoors
- ComponentMemory
Abstract连通性沿 k 与ρ改变攻防，且用户/物品与早期/稳态需要分开看。
作者在 AgentCF 上研究连通性如何改变多智能体协同过滤的攻防，复现已有方法而不是提出新载荷。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2607.14611Jul 16
论文评测 Claude Code 与 Codex 记忆文件中的提示注入风险
评测编码 Agent 记忆文件中提示注入的跨会话影响
arXiv
2607.14611
Published
Jul 16
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Haiku 4.5, Claude Opus 4.7, GPT-5.2 and others4
- AttacksPoisoning and backdoors
- ComponentMemory
Abstract已植入记忆文件的载荷可以跨会话影响 Claude Code 与 Codex，攻击成功与载荷是否留下是两种不同的失败。
Bad Memory 在沙箱合成工作区里评测文件型持久记忆上的提示注入，比较载荷能否改变当前会话，以及能否在后续会话中留下或叠加。
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 2605.08460May 9
论文建模多智能体网络中的子智能体继承攻击面
建模并利用多智能体网络中子智能体生成时的记忆继承漏洞
arXiv
2605.08460
Published
May 9
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
MiniMax M2.5, Llama-4-Maverick-17B-128E-Instruct-FP8, Qwen3.5-Plus and others5
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract形式化子智能体继承，在 OpenClaw 上演示四类编排层漏洞并提出防御。
作者对多智能体网络里的子智能体继承做形式化分析，并用开源框架上的 PoC 演示编排层如何让单点妥协继续扩散。
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

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

研究者提出 PackHallu：经规则文件提示注入对编码 Agent 发起包幻觉攻击

PersistBD: attackers can strengthen backdoors before release so that they maintain high attack success rates even after developer SFT and RL.

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

Memetic Trojans：利用社交传染在 LLM Agent 网络中传播对抗载荷

TrustFork：显示身份如何劫持 LLM 智能体编排的权限

Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

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

CodePoisonRAG：针对检索增强代码生成的知识投毒攻击

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

Researchers propose context privilege escalation attack, affecting 12 agent frameworks

多智能体协同过滤系统的连接性攻击与防御研究

论文评测 Claude Code 与 Codex 记忆文件中的提示注入风险

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

论文建模多智能体网络中的子智能体继承攻击面

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