Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.

Impact：Data and privacy leaks Attack surface / entry point：Tool and skill descriptions Attack surface / entry point：Training data Attack surface / entry point：Distribution channels Clear all

Another 261papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.12524Oct 8
An exploration of attacks on AI agent systems
重测并扩展对 AI Agent 的提示注入，并用 Agent Card 欺骗操纵 A2A 选择
arXiv
2610.12524
Published
Oct 8
Layer
Application layer
Setting
AI Agent
Evaluated models
Ollama Mistral 0.9.5, llama3-8b-8192, gemini-2.0-flash-lite and others5
- AttacksPrompt injection
- TechniqueEncoding and obfuscation
- ComponentMCP and skills
Abstract单智能体过滤与分类可被格式或措辞绕过，A2A 选卡还会偏向名称和描述。
作者在自建的 LangChain、AutoGen 和 A2A 系统上重测提示注入，并改 Agent Card 看选择是否偏移。摘要称试验主要凸显单智能体弱点，同时把攻击扩到多智能体。
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 2610.06636Oct 6
差分隐私混合公共数据集提升隐私学习效果
提出 DP-MixMin，私有学习公开数据混合并做差分隐私微调
arXiv
2610.06636
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
ResNet-18, GPT-2 Medium
- AttacksExtraction and theft
AbstractDP-MixMin 私下学公开混合再 DP 微调，胸片 macro AUC 与邮件困惑度优于均匀混合。
DP-MixMin 是一条端到端的差分隐私训练流程：先私下决定多个公开数据集的预训练混合，再预训练并在敏感数据上 DP 微调。作者称这是首个这样的流程。
Paper analysisRead analysis
AttacksarXiv 2610.05453Oct 5
研究者提出 Privacy-Leaking Watermarks，可在本地多模态模型中泄露对话隐私
提出 PLW，用微调把先前对话敏感触发编码进后续生成图像
arXiv
2610.05453
Published
Oct 5
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
OmniGen2, BAGEL-7B
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
AbstractPLW 把先前对话线索写成后续图像中的隐水印，检出随触发、模型和间隔变化。
Paper analysisRead analysis
DefensesarXiv 2610.04426Oct 3
UnAct：无需梯度的定向激活干预实现类别遗忘
提出 UnAct，仅以前向激活干预从分类器中遗忘指定类别
arXiv
2610.04426
Published
Oct 3
Layer
Model layer
Setting
Models and APIs
Evaluated models
ResNet-18, ViT-B/16
- DefensesModel hardening
- AttacksExtraction and theft
AbstractUnAct 用前向激活做类别遗忘。
UnAct 是一种事后类别遗忘：删除请求可以只有少量该类图像，且没有标签和保留数据。它不用梯度，只对遗忘图像做前向。编辑对象是分类器所读的后期单元。
Paper analysisRead analysis
AttacksarXiv 2610.01365Oct 1
ReGap：无需真实隐私数据即可通过微调重新提取模型隐私关联
提出 ReGap，用自生成伪监督微调恢复模型中的隐私关联
arXiv
2610.01365
Published
Oct 1
Layer
Training and data layer
Setting
Models and APIs
Attacker
White-box, Gray-box
Evaluated models
GPT-2 Small, GPT-2 Medium, GPT-2 Large and others6
- AttacksExtraction and theft
- ComponentFine-tuning and open weights
Abstract提出无真实私有监督的恢复攻击 ReGap，实验显示微调可通过自生成数据唤醒模型潜在隐私关联，突显后适应隐私风险。
Paper analysisRead analysis
DefensesarXiv 2609.37858Sep 29
存储不等于策略：面向 LLM 遗忘的状态条件支持控制
提出 Intervention Score 与 DIR-R，按干预效果选择并修订遗忘参数支持
arXiv
2609.37858
Published
Sep 29
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama 3 8B, Gemma 2 2B, Qwen2.5-7B and others4
- DefensesModel hardening
- AttacksExtraction and theft
Abstract作者把局部化遗忘拆成初始干预选择和检查点修订，并在三个设置里分别给证据和边界。
Storage Is Not Strategy 研究局部化 LLM 遗忘里两个常被混在一起的决定：一开始该更新哪些参数，以及优化改变模型之后这个选择要不要改。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.34092Sep 28
机器遗忘在 ASR 中是否有效：arXiv 论文评估现有算法与评测工具
arXiv
2609.34092
Published
Sep 28
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
E-Branchformer
- DefensesModel hardening
- AttacksExtraction and theft
- ComponentAudio
Abstract梯度上升类方法更接近简单评测下的重训参照，复杂方法会被知情攻击认出，多说话人更差。
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 2609.18217Sep 16
研究：跨通道碎片化攻击可绕过 MCP 单通道防御
提出跨通道分段攻击，利用 MCP 隐式信任外发敏感文件
arXiv
2609.18217
Published
Sep 16
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-4o, GPT-4o-mini, GPT-5.4 and others15
- AttacksPrompt injection
- TechniqueEncoding and obfuscation
- ComponentMCP and skills
Abstract论文揭示了 MCP 多通道隐式信任层级，通过跨通道分段与协议级利用突破现有防御，展示了严重的凭证外发风险。
Paper analysisRead analysis
DefensesarXiv 2609.01677Sep 1
Skill-as-API：面向智能体软件工程的机密多智能体协作协议
提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词
arXiv
2609.01677
Published
Sep 1
Layer
Application layer
Setting
Multi-agent systems, coding agent
- DefensesInstruction–data separation
- AttacksExtraction and theft
- ComponentMCP and skills
Abstract协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。
Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。
Paper analysisRead analysis
AttacksarXiv 2608.27800Aug 28
ContextLeak：通过恶意工具窃取 LLM Agent 运行时上下文
提出 ContextLeak，用强化学习优化恶意工具描述，诱导 Agent 外泄运行时上下文
arXiv
2608.27800
Published
Aug 28
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen-3-8B, GPT-OSS-20B, Gemma-4-E4B-it and others11
- AttacksPrompt injection
- TechniqueSelection manipulation
- ComponentMCP and skills
Paper analysisRead analysis
AttacksarXiv 2608.25776Aug 26
EvoMal attack uses self-poisoning of self-evolving coding agents to achieve worm-like propagation
提出 EVOMAL，诱导自演化编码 Agent 在创建技能时自我投毒并蠕虫传播
arXiv
2608.25776
Published
Aug 26
Layer
Application layer
Setting
coding agent
Evaluated models
Devstral-Small-2, Gemma-4-31B-IT, Qwen3-Coder-Next and others7
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMCP and skills
Abstract论文指出了自演化智能体模仿检索代码的自我毒化漏洞，提出 EVOMAL 攻击与防御，阐明了供应链新风险。
Paper analysisRead analysis
DefensesarXiv 2608.24017Aug 25
WebMCP-Phalanx：为浏览器内 LLM Agent 工具调用建立信任边界
提出 WebMCP-Phalanx，用能力凭证与双智能体隔离浏览器工具调用
arXiv
2608.24017
Published
Aug 25
Layer
Application layer
Setting
web agent
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentMCP and skills
AbstractPhalanx 用浏览器凭证绑定工具所有权，Q/P 分离拦住描述注入，工具名与返回值仍有残留。
WebMCP-Phalanx针对浏览器里的 WebMCP 智能体：在 SOP 下补工具所有权，并把语义检查从有工具权的执行中分开。
Paper analysisRead analysis
DefensesarXiv 2608.22868Aug 24
AgentFlow：面向 LLM 智能体系统的流中心策略语言与运行时防护框架
提出 AgentFlow 流策略语言与运行时框架，约束智能体跨步数据流
arXiv
2608.22868
Published
Aug 24
Layer
Application layer
Setting
AI Agent
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
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
DefensesarXiv 2607.13336Jul 15
TC-UAP：针对图像转视频与微调定制的通用视频保护方法
提出 TC-UAP，用身份级多帧扰动保护视频免被定制复现身份
arXiv
2607.13336
Published
Jul 15
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
LTX-2.3, Wan2.2-5B
- ComponentVideo
AbstractTC-UAP 以可复用的时间一致扰动干扰两类定制共用的 VAE 隐空间。
作者要解决的是：发布前如何给视频加不可见扰动，使片段既不能被拿去微调视频扩散模型，也不能被抽帧做 image-to-video。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2606.15899Jun 15
SkillVetBench：用 LLM-as-Judge 评估开源 LLM Agent 技能的多维安全风险
提出 SkillVetBench 评估开源 Agent 技能的多维安全风险
arXiv
2606.15899
Published
Jun 15
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen2.5-14B-Instruct, Qwen2.5-32B, Llama-3.1-70B and others6
- AttacksPoisoning and backdoors
- ComponentMCP and skills
Abstract公开排行榜用 LLM-as-Judge 给技能分列 SARS 与 CVSS，并对照市场官方审查。
Paper analysisRead analysis
DefensesarXiv 2605.17380May 17
Uber proposes ADR enterprise-level agent detection system, deployed on 7,200 hosts for ten months
提出企业级检测系统 ADR，识别编程 Agent 的提示注入与恶意 MCP
arXiv
2605.17380
Published
May 17
Layer
Application layer
Setting
coding agent
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentMCP and skills
Abstract提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统，并在生产环境中验证了有效性。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2604.01438Apr 2
ClawSafety: Safe LLM, Unsafe Agent
提出 ClawSafety，评测个人智能体读到对抗工件后是否执行有害动作
arXiv
2604.01438
Published
Apr 2
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Sonnet 4.6, GPT-5.1, Gemini 2.5 Pro and others5
- AttacksPrompt injection
- ComponentMCP and skills
Paper analysisRead analysis

You have reached the end

AI Safety Daily

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