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

Oct 12 · Monday

All papers

Found 44 papers

Filter5

Attack type

Jailbreaks7 Prompt injection14 Poisoning and backdoors8 Extraction and theft8 Detection evasion8 Malicious use4

Attack technique

Automated search7 Defense-targeted3 Dormant triggers5

Defense type

Detection and filtering6 Permissions and approval3

Impact

Harmful content7 Unauthorized actions12 Data and privacy leaks12 Output manipulation11

System component

MCP and skills5 RAG11 Guardrails and judges11 Monitors3 Permissions and sandboxing3

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.

System type：LLM applications System type：coding agent Attack surface / entry point：User input Attack surface / entry point：Weights and gradients Layer：Application layer Clear all

Another 254papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.12292Oct 9
The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
arXiv
2610.12292
Published
Oct 9
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
LAYA-TD, LAYA-EN, LAYA-ML and others5
- AttacksDetection evasion
- ComponentGuardrails and judges
AbstractThe authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.
Paper analysisRead analysis
AttacksarXiv 2610.10742Oct 8
BRANCH 方法绕过 6 套多扫描器护栏系统
提出 BRANCH 方法，用分支搜索绕过多扫描器护栏
arXiv
2610.10742
Published
Oct 8
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Meta Llama Guard 3 8B, Meta Llama Guard 7B, Meta Llama Guard 3 1B and others18
- AttacksDetection evasion
- TechniqueAutomated search
- ComponentGuardrails and judges
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 2610.07276Oct 6
SAFESHIELD：小语言模型部署时安全的决策组织框架
提出 SAFESHIELD，组织小语言模型部署时的安全决策
arXiv
2610.07276
Published
Oct 6
Layer
Application layer
Setting
LLM applications
Evaluated models
Qwen3-4B-Instruct
- AttacksJailbreaks
- RiskHallucination and fabrication
- ComponentRAG
AbstractSAFESHIELD 用可审计决策轨迹组织 SLM 部署时的四项安全决策，并报告协调依赖影响端到端结果。
SAFESHIELD 是面向小语言模型的部署时安全框架，把运行时安全从单项审核改写成可检查的决策过程。
Paper analysisRead analysis
AttacksarXiv 2610.04985Oct 4
研究揭示 Jev 作为应用决策层的安全与隐私风险
评估应用决策层的输入注入与隐私推断风险
arXiv
2610.04985
Published
Oct 4
Layer
Application layer
Setting
LLM applications
Attacker
Black-box, Gray-box
Evaluated models
Jev, NanoJev
- AttacksPrompt injection
- TechniqueRole-play and persuasion
AbstractJev 的类型化决策可被输入与训练操纵，也会泄露信息，并同时支持检测与滥用。
Jev 是 TypeSafe 的 System One 模型，把应用 state 和固定问题变成 Choice、Noul 或 Score 的类型化决策与概率。作者用官方 API 和可改训练的 NanoJev，考察它作为决策层时的操纵、泄露与双重用途。
Paper analysisRead analysis
DefensesarXiv 2610.04412Oct 3
论文研究 LLM 数字孪生参与增强民主时的提示注入脆弱性
提出检测、结构化与 GSPO 流程，降低共识生成的提示注入错位
arXiv
2610.04412
Published
Oct 3
Layer
Application layer
Setting
LLM applications, Multi-agent systems
Evaluated models
LLaMA-2 7B, LLaMA-3 8B, GPT 3.5 Turbo and others14
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract三章依次做个体偏好预测、政党知识图谱审议，以及共识生成对提示注入的脆弱性与一条防御流程。
这是一篇把 LLM 数字孪生放进增强民主的博士论文，分个体表示、政党聚合和共识生成的提示注入三章。
Paper analysisRead analysis
AttacksarXiv 2610.03857Oct 3
研究者提出 EviLLM 攻击：通过被入侵账号向 AI 代码生成流程注入漏洞
提出 EviLLM，经账户指令或插件向代码生成流程注入漏洞
arXiv
2610.03857
Published
Oct 3
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-4o, Llama 3.2 (3B)
- AttacksPrompt injection
- TechniqueDefense-targeted
Paper analysisRead analysis
DefensesarXiv 2610.02432Oct 2
论文提出 LLM 输入扰动鲁棒性度量，并发布 ASA 攻击与 AttestMCP 防护
提出 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感
arXiv
2610.02432
Published
Oct 2
Layer
Application layer
Setting
LLM applications, AI Agent
Attacker
Black-box
Evaluated models
Gemma-3-27B-Instruct, Gemma-3-4B-Instruct, Llama-3.2-3B-Instruct and others12
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Paper analysisRead analysis
AttacksarXiv 2610.01871Oct 1
研究者提出 IMMRAG 攻击，可从多模态 RAG 数据存储中提取医学与文档图像
提出 imMRAG 攻击，从多模态 RAG 私有图像库提取内容
arXiv
2610.01871
Published
Oct 1
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Lumina-mGPT, Gemini 2.5 Flash Image Preview, CLIP ViT-B/16 and others5
- AttacksExtraction and theft
- TechniqueCross-modal payloads
- ComponentRAG
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 2609.36326Sep 29
PILLAR：面向增强检索的私有倒排索引词法查找
提出 PILLAR，用私有词法预筛与客户端重排保护 RAG 查询
arXiv
2609.36326
Published
Sep 29
Layer
Application layer
Setting
LLM applications
- ComponentRAG
AbstractPILLAR 用固定模式的私有 BM25 预筛加本地嵌入重排，在两基准上换取延迟或质量。
PILLAR 是面向公开语料的隐私 RAG：半诚实服务器学不到查询词项和访问模式，客户端仍拿到用于增强生成的 k 篇文档。
Paper analysisRead analysis
AttacksarXiv 2609.33910Sep 28
论文提出残留授权重放攻击：长期运行 Agent 的授权可跨任务复用
提出残余权限重放攻击，跨任务复用长期 Agent 的历史授权绕过确认
arXiv
2609.33910
Published
Sep 28
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-4.1, Gemini-3.1-Flash-Lite, Qwen3-14B and others6
- AttacksPrompt injection
- TechniqueDefense-targeted
- ComponentPermissions and sandboxing
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
Risky behaviorarXiv 2609.30266Sep 25
研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹
测试编程智能体被诱导或自主篡改自身执行轨迹的行为
arXiv
2609.30266
Published
Sep 25
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6-Sol, GPT-6-Sol, Opus-5 and others11
- AttacksMalicious use
- RiskDeception and scheming
- ComponentMonitors
Abstract论文评估了本地智能体的轨迹防篡改能力，发现其可因外部指令或奖励追求而清除执行证据，亟需建立独立拦截记录机制。
这是一项针对本地大模型智能体执行轨迹完整性与安全防篡改边界的实证研究。
Paper analysisRead analysis
AttacksarXiv 2609.29130Sep 24
ClaimMirage：域名中的自我声明如何改变 LLM 威胁判断
提出 ClaimMirage，以域名自述声称改变 LLM 威胁告警判断
arXiv
2609.29130
Published
Sep 24
Layer
Application layer
Setting
LLM applications
Evaluated models
Llama 3.3 70B Instruct-Turbo, Gemma 3 4B it, Gemma 3 12B it and others5
- AttacksDetection evasion
- ComponentGuardrails and judges
Abstract作者称自述声称可增减告警。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.15017Sep 14
PIDS-Bench：在过度防御、混淆与分布偏移下评测提示注入检测器
提出 PIDS-Bench，评测提示注入检测器在过度防御与分布偏移下的表现
arXiv
2609.15017
Published
Sep 14
Layer
Application layer
Setting
LLM applications
Evaluated models
TF-IDF + logistic regression, DistilBERT, DeBERTa-v3-FT and others7
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractPIDS-Bench 显示高分布内 F1 仍会过度拦截外部来源的安全相关良性输入。
PIDS-Bench 是一个冻结的检测器级基准，用来在固定阈值下同时看提示注入检测和良性误报。
Paper analysisRead analysis
AttacksarXiv 2609.14649Sep 14
CIG-MIA：利用上下文信息增益对 RAG 系统发起成员推断攻击
提出 CIG-MIA，用上下文信息增益推断 RAG 知识库成员身份
arXiv
2609.14649
Published
Sep 14
Layer
Application layer
Setting
LLM applications
Attacker
Gray-box, Black-box
Evaluated models
Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3, Llama-2-13b-chat-hf and others6
- AttacksExtraction and theft
- ComponentRAG
AbstractCIG-MIA 用注入前后的答案似然差推断 RAG 库成员，灰盒可分性高于所列基线。
CIG-MIA 是针对 RAG 外部知识库的成员推断攻击，同时覆盖灰盒和纯文本黑盒。
Paper analysisRead analysis
DefensesarXiv 2609.10992Sep 10
拆解 LLM 交互中的隐私-效用权衡：Veilmind-4B 意图驱动本地保护框架
提出意图驱动本地框架 Veilmind，净化发往远程模型的提示词
arXiv
2609.10992
Published
Sep 10
Layer
Application layer
Setting
LLM applications
Evaluated models
Veilmind-4B
- DefensesInstruction–data separation
Abstract本地模型按意图净化提示词，在 Uprise 上给出两个隐私-效用工作点。
本地侧的意图驱动净化，用来降低用户提示词发往不受信任远程模型时的敏感属性暴露。
Paper analysisRead analysis
AttacksarXiv 2608.27439Aug 28
RedEvoAgent：以经验驱动技能演化的自动红队智能体
提出 RedEvoAgent，演化攻击技能对黑盒智能体做自动红队
arXiv
2608.27439
Published
Aug 28
Layer
Application layer
Setting
coding agent
Attacker
Black-box
Evaluated models
MiniMax-M2.5, DeepSeek-V4-Flash, Qwen3.5-35B
- AttacksJailbreaks
- TechniqueAutomated search
AbstractRedEvoAgent 用验证棘轮演化可读攻击技能，在两种产品级 harness 上多数设置高于固定工具与红队基线。
RedEvoAgent 是面向产品级 black-box 智能体的自动红队方法，用一份可演化、人类可读的攻击技能编排多个越狱工具。。
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

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

Attacker access

Attack surface / entry point

Layer

System component