Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.

Attack type：Poisoning and backdoors Attack surface / entry point：User input Clear all

Another 265papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.12644Oct 9
Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.
Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.
arXiv
2610.12644
Published
Oct 9
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentReasoning chains
AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.
Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.
Paper analysisRead analysis
AttacksarXiv 2610.07723Oct 6
Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.
提出回答端后门，让模型自生成触发词以在干净有害请求下绕过拒答
arXiv
2610.07723
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.3, Gemma-7B-it and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract论文提出了多轮对话中回答端自生成触发词绕过安全拒绝的后门攻击，指出输入端防护存在盲区。
Paper analysisRead analysis
DefensesarXiv 2610.07657Oct 6
DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降
实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击
arXiv
2610.07657
Published
Oct 6
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractDEFER 把确定性检查放在 judge 之前。
DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。
Paper analysisRead analysis
AttacksarXiv 2610.04589Oct 3
StegoMemory red team testing: agent persistent memory can be used as a cross-session covert channel
提出 StegoMemory，评测智能体持久记忆作为跨会话隐写信道
arXiv
2610.04589
Published
Oct 3
Layer
Application layer
Setting
AI Agent
Evaluated models
Llama 3.1 405B, Claude 3.5 Sonnet, GPT-4o and others13
- AttacksPoisoning and backdoors
- TechniqueEncoding and obfuscation
- ComponentMemory
Abstract研究揭示智能体持久记忆可作为隐蔽信道跨会话传输机密，写入持久化是主要防御瓶颈，呼吁建立记忆完整性防御。
Paper analysisRead analysis
DefensesarXiv 2609.39548Sep 30
NDDL：用正常扩散动力学为文生图模型做后门防御
提出 NDDL，用良性扩散轨迹检测文生图后门提示并定位触发 token
arXiv
2609.39548
Published
Sep 30
Layer
Model layer
Setting
Models and APIs
Evaluated models
Stable Diffusion v1.5, Stable Diffusion XL, Stable Diffusion v3.5 and others4
- DefensesMonitoring and auditing
- AttacksPoisoning and backdoors
- ComponentImage generation
AbstractNDDL 从良性扩散轨迹学习正常转移，用动态不一致检测后门并定位触发 token。
NDDL 是面向文生图扩散模型的后门防御：防御者只有白盒模型访问和良性提示词，没有后门先验，需要区分后门提示词并找出触发 token。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.39146Sep 30
MADBench：多智能体辩论安全性评测基准发布
提出 MADBench，评测多智能体辩论是吸收还是放大对抗影响
arXiv
2609.39146
Published
Sep 30
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
gpt-4o, GPT-5, GPT-6 Astra
- AttacksPrompt injection
- ComponentRAG
AbstractMADBench 显示辩论能吸收部分准确率攻击，同时放大未授权读写。
MADBench 是一个评测多智能体辩论安全性的基准，用来看攻击是被辩论吸收还是被放大。
Paper analysisRead analysis
AttacksarXiv 2609.38270Sep 29
VirusCascade：劫持 LLM 推荐智能体的协同反思机制
提出 VirusCascade，联合操纵商品描述与交互轨迹以劫持推荐智能体协同反思
arXiv
2609.38270
Published
Sep 29
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
AgentCF, AgentSEQ, AgentRAG and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract作者把反思写回视为推广攻击入口，并用联合操纵和诊断探针研究其持续与传播。
VirusCascade 是针对推荐智能体协作反思的 black-box targeted promotion 攻击研究。 攻击者只改商品描述和少量账号的普通交互，试图让目标商品获得更多良性用户曝光。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.34790Sep 28
CoSec：面向社区场景的 LLM Agent 安全基准
用 CoSec 评测社区 Agent 是否越界披露受保护信息
arXiv
2609.34790
Published
Sep 28
Layer
Application layer
Setting
AI Agent
Evaluated models
OpenClaw with Gemini 3.1 Pro, OpenClaw with Qwen 3.8 Max, OpenClaw with MiniMax M2.5 and others13
- AttacksPrompt injection
- ComponentMemory
Paper analysisRead analysis
AttacksarXiv 2609.33985Sep 28
研究：众包微调数据投毒可放大专有指令抽取
提出主题锚点投毒，放大众包微调后的专有指令提取
arXiv
2609.33985
Published
Sep 28
Layer
Training and data layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Qwen2.5-7B-Instruct, Qwen2.5-14B-Instruct, Llama-3.1-8B-Instruct and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract论文提出基于主题锚点的数据中毒攻击，证明低比例的中毒样本可在黑盒条件下隐蔽放大微调指令泄漏。
Paper analysisRead analysis
AttacksarXiv 2609.37468Sep 26
论文提出针对 Agentic RAG 的检索器后门攻击与 DOU 隐藏方法
提出检索器后门攻击操纵智能体搜索，并用 DOU 逃避检测
arXiv
2609.37468
Published
Sep 26
Layer
Application layer
Setting
AI Agent
Evaluated models
E5, Contriever-MSMARCO
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentRAG
Abstract论文展示了通过恶意检索器操纵智能体多轮搜索并利用诱饵重塑表征隐蔽后门的可行性与系统风险。
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 2609.22818Sep 19
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
Sep 19
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。
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
DefensesarXiv 2609.16098Sep 14
研究者提出面向工具集成 LLM Agent 的通用对抗攻击防御方法
提出 ATF 与 NTR，过滤或恢复工具集以阻止 Agent 调用攻击工具
arXiv
2609.16098
Published
Sep 14
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemma2-9B, Qwen2-7B, LLaMA3-8B and others7
- DefensesPermissions and approval
- AttacksPrompt injection
Paper analysisRead analysis
AttacksarXiv 2609.02035Sep 2
ISM：通过语义匹配隐式操纵 LLM Agent 的技能选择
提出 ISM，用语义匹配隐式操纵 Agent 技能选择
arXiv
2609.02035
Published
Sep 2
Layer
Application layer
Setting
AI Agent
Evaluated models
Llama-2-7B, Llama-3-8B, Llama-3.1-8B and others8
- AttacksPoisoning and backdoors
- TechniqueSelection manipulation
- ComponentMCP and skills
Paper analysisRead analysis
DefensesarXiv 2609.29647Aug 29
AgentKernel：面向 Agent 的可信原生操作系统内核
提出 AgentKernel，用四支柱强制中介 Agent 的输入、工具与记忆
arXiv
2609.29647
Published
Aug 29
Layer
Application layer
Setting
AI Agent
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
AbstractAgentKernel 是四支柱智能体 OS 设计，安全论证未附带实测数字。
AgentKernel 是把安全做成组织原则的智能体 OS 架构，不是带跑分的攻防评测。
Paper analysisRead analysis
DefensesarXiv 2608.21101Aug 21
ClawSentry：面向自主 LLM Agent 的渐进式多层安全监控网关
提出 ClawSentry 多层监控网关，在技能准入和运行时拦截恶意技能与隐藏指令
arXiv
2608.21101
Published
Aug 21
Layer
Application layer
Setting
coding agent
Evaluated models
Codex/GPT-5.4, Codex/GPT-5.5, Claude Code/GLM-5.1 and others6
- DefensesMonitoring and auditing
- AttacksPoisoning and backdoors
- ComponentMCP and skills
AbstractClawSentry 用包准入、三级运行时门控和反绕过，压低 skill 攻击并保住干净任务。
ClawSentry 是挂在智能体运行时之外的安全监督网关，用来同时盖住 skill 执行的多个生命周期边界，并把已被拒绝的效果记到会话里。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.12851Aug 13
研究者提出 SkillMisevo-Bench，量化自改进 Agent 的技能误演化风险
提出 SkillMisevo-Bench，量化自改进 Agent 的技能误演化
arXiv
2608.12851
Published
Aug 13
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Code, Codex, Hermes and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Paper analysisRead analysis
AttacksarXiv 2608.09577Aug 10
ElasticBack：通过触发词与规则耦合在 LLM Agent 技能中植入条件后门
提出 ElasticBack，在单个 Agent 技能中植入条件后门
arXiv
2608.09577
Published
Aug 10
Layer
Application layer
Setting
coding agent
Evaluated models
GLM-5.2, MiniMax-M3, GPT-5.4 and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMCP and skills
AbstractElasticBack 用冻结规则加遗传搜索演化 trigger，在单 skill 上做条件后门。
ElasticBack 是放在 LLM agent 单个 skill 里的条件后门攻击。。
Paper analysisRead analysis
AttacksarXiv 2608.03844Aug 4
MAFIA：针对带审计 LLM Agent 的查询式记忆投毒攻击
提出 MAFIA，以探测放置与事实伪装对带审计 Agent 做查询式记忆投毒
arXiv
2608.03844
Published
Aug 4
Layer
Application layer
Setting
AI Agent
Evaluated models
gpt-5.4-mini, Gemini, ProtectAI and others8
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Paper analysisRead analysis

AI Safety Daily

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