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

Oct 12 · Monday

All papers

Found 12 papers

Filter4

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.

Impact：Data and privacy leaks Attack surface / entry point：Tool responses Attack surface / entry point：Code repositories and dependencies Layer：Application layer Clear all

Another 240papers do not have category tags yet and are not included in filtered results.

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
AttacksarXiv 2610.01768Oct 1
LLMLeak：借 LLM 合法网页抓取实施隐蔽数据外泄
提出 LLMLeak，借合法网页抓取把 URL 中的秘密隐蔽外传
arXiv
2610.01768
Published
Oct 1
Layer
Application layer
Setting
coding agent
Evaluated models
Meta-Llama-3.3-70B-Instruct, Meta-Llama-4-Scout-17B-16E-Instruct, Meta-Llama-3.1-8B-Instruct and others18
- AttacksMalicious use
Abstract作者称第三方外传可发生于正常网页获取，防护需考虑工具请求而不只考虑提示注入。
LLMLeak 是利用网页获取请求携带预先编码秘密的隐蔽通道攻击。它关注恶意软件已能读取数据、却因网络限制或监控无法直接外传的情形。
Paper analysisRead analysis
DefensesarXiv 2609.33371Sep 27
论文提出保险库中介执行边界，评估 LLM Agent 的 API 凭据处理风险
提出并评测保险库中介执行边界，隔离 Agent 的 API 凭据
arXiv
2609.33371
Published
Sep 27
Layer
Application layer
Setting
AI Agent
Evaluated models
Corvic Security Vault
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Abstract作者称，凭据分离可减少披露路径，但权限、操作授权和配置验证仍需独立控制。
这是一项智能体 API 凭据威胁分析及 Vault 执行边界的功能评测。作者关心的不是模型能否承诺保密，而是认证材料是否会进入模型、日志、记忆和执行代码。
Paper analysisRead analysis
AttacksarXiv 2609.27542Sep 23
Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring
提出控制标记注入，清空工具 Agent 的思维链以绕过推理监控
arXiv
2609.27542
Published
Sep 23
Layer
Application layer
Setting
AI Agent
Evaluated models
openai/gpt-oss-20b, google/gemma-4-26B-A4B-it, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4
- AttacksPrompt injection
- TechniqueConversation structure manipulation
- ComponentReasoning chains
Abstract论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过，且工具执行受解析器宽容度影响。
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 2609.07529Sep 7
CoER：用对抗协同演化与精炼防御自适应间接提示注入
提出 CoER，用对抗共进化与精炼训练工具智能体抵御自适应间接提示注入
arXiv
2609.07529
Published
Sep 7
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen3.5-9B
- DefensesModel hardening
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2609.04875Sep 4
Forgetting without restart: execution-state forgetting for stateful LLM agents
Proposes execution-state forgetting, using provenance-guided selective replay to purify stateful agents
arXiv
2609.04875
Published
Sep 4
Layer
Application layer
Setting
AI Agent
Evaluated models
Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
- AttacksPrompt injection
- ComponentMemory
AbstractSelective replay concatenates the clean prefix with the sanitized suffix, and main-table metrics match full reset.
This work defines forgetting in long-horizon agents as runtime counterfactual equivalence, rather than deleting a plaintext memory.
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 2607.26115Jul 29
OpenAI releases GPT-Red: training automated red-teaming agents through self-play
训练自博弈红队智能体 GPT-Red，规模化生成提示注入与越狱攻击
arXiv
2607.26115
Published
Jul 29
Layer
Application layer
Setting
AI Agent
Attacker
Black-box
Evaluated models
GPT-5.6, GPT-5.5, GPT-5.4 and others8
- AttacksPrompt injection
- TechniqueAutomated search
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
Evaluation and benchmarksarXiv 2605.01970May 4
Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses on LLM Agents
构建 Trojan Hippo Bench，评测 Agent 持久记忆投毒与外泄
arXiv
2605.01970
Published
May 4
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemini 3.1 Pro, GPT-5-mini, GPT-5
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract论文提出了评测智能体持久化记忆攻击与防御的 Trojan Hippo Bench，揭示了潜伏攻击威胁及内存防御的安全与效用权衡。
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

Defense type

Impact

System type

Attack surface / entry point

Layer

System component

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

LLMLeak：借 LLM 合法网页抓取实施隐蔽数据外泄

论文提出保险库中介执行边界，评估 LLM Agent 的 API 凭据处理风险

Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring

研究：跨通道碎片化攻击可绕过 MCP 单通道防御

CoER：用对抗协同演化与精炼防御自适应间接提示注入

Forgetting without restart: execution-state forgetting for stateful LLM agents

WebMCP-Phalanx：为浏览器内 LLM Agent 工具调用建立信任边界

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

OpenAI releases GPT-Red: training automated red-teaming agents through self-play

论文评测 Claude Code 与 Codex 记忆文件中的提示注入风险

Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses on LLM Agents