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

Oct 12 · Monday

All papers

Found 49 papers

Filter3

Attack type

Prompt injection28 Poisoning and backdoors19 Extraction and theft5

Attack technique

Gradient and representation optimization6 Automated search10 Encoding and obfuscation4 Cross-modal payloads4 Side channels4 Defense-targeted5 Dormant triggers18

Impact

Unauthorized actions15 Data and privacy leaks12 Output manipulation17 Availability and reliability3

System component

MCP and skills5 Memory18 RAG4 Guardrails and judges4 Reasoning chains4 Vision4 Multimodal4

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.

Attack surface / entry point：Web pages and interfaces Attack surface / entry point：Memory writes Attack surface / entry point：Inference services and hardware Clear all

Another 254papers 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 2610.12524Oct 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 2610.09981Oct 7
研究：LLM 路由决策日志可推断用户医疗、自伤等敏感话题
提出利用路由元数据推断敏感话题的侧信道攻击
arXiv
2610.09981
Published
Oct 7
Layer
Infrastructure layer
Setting
LLM applications
Evaluated models
RouteLLM (BERT router), notdiamond-0001, Vela (vLLM Semantic Router)
- AttacksExtraction and theft
- TechniqueSide channels
Abstract论文揭示并测量了 LLM 路由决策在无文本日志中的敏感话题泄露，验证了按类别公平性防御的有效性与边界。
Paper analysisRead analysis
AttacksarXiv 2610.09240Oct 7
WebMirage hijacks visual web agents' browser operations with adversarial images
提出 WebMirage，用局部对抗图像劫持视觉网页 Agent 的浏览器操作
arXiv
2610.09240
Published
Oct 7
Layer
Application layer
Setting
web agent
Evaluated models
LLaVA-v1.5-13B, LLaVA-v1.6-34B, MiniCPM-o-8B and others6
- AttacksPrompt injection
- TechniqueGradient and representation optimization
- ComponentVision
Abstract论文提出了针对网络智能体的端到端视觉红队框架 WebMirage，揭示了从视觉定位到浏览器执行的安全脆弱性。
WebMirage 是一个面向视觉定位网络智能体的流水线感知端到端红队攻击框架。
Paper analysisRead analysis
AttacksarXiv 2610.08951Oct 7
ASPIRE：面向 LLM Agent 的开放式提示注入红队引擎
提出 ASPIRE 行为图搜索，开放式发现 Agent 提示注入漏洞
arXiv
2610.08951
Published
Oct 7
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemini-3.7-Flash, DeepSeek-V4-Flash, Gemini-2.5-flash
- AttacksPrompt injection
- TechniqueAutomated search
AbstractASPIRE 把提示注入红队从载荷优化改成行为图引导的开放式漏洞发现。
ASPIRE 是给搭建方用的智能体提示注入红队引擎，目标是开放式画出可利用的行为路径，而不是在固定任务上打磨一条载荷。
Paper analysisRead analysis
AttacksarXiv 2610.07645Oct 6
SkillPoison：用成功经验投毒自进化 Agent 的技能形成
提出 SkillPoison，用局部有效的成功经验诱导自进化 Agent 形成过度泛化技能
arXiv
2610.07645
Published
Oct 6
Layer
Application layer
Setting
AI Agent
Evaluated models
deepseek-v4-flash, Qwen V3.8 Flash, GPT-5.5
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
AbstractSkillPoison 通过局部有效且验证成功的经验诱导技能过度泛化，在多个评测基准上实现了持久的下游攻击影响。
SkillPoison 提出了一种针对自进化智能体经验到技能形成过程的攻击范式，通过组织已验证的成功经验诱导技能过度泛化。
Paper analysisRead analysis
AttacksarXiv 2610.06848Oct 6
TranScope：利用 CPU 性能计数器对 Transformer 做成员推断攻击
提出 TRANSCOPE，用 CPU 硬件计数器推断训练集成员
arXiv
2610.06848
Published
Oct 6
Layer
Infrastructure layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
BERT (4.4M-340M), ViT (22M-307M), Pythia (70M-2.8B) and others5
- AttacksExtraction and theft
- TechniqueSide channels
AbstractTRANSCOPE 揭示了分词器在嵌入表引发的硬件访问局部性差异，证实微架构计数器可突破恒定时间与置信度遮蔽防御。
Paper analysisRead analysis
AttacksarXiv 2610.05894Oct 5
研究者提出闭环偏见注入攻击
提出闭环激活引导，在扩散语言模型去噪过程中注入定向偏见
arXiv
2610.05894
Published
Oct 5
Layer
Model layer
Setting
Models and APIs
Attacker
Gray-box
Evaluated models
LLaDA-8B-Instruct, Dream-v0-Instruct-7B, LLaDA-MoE-7B-A1B-Instruct
- AttacksModel tampering
- TechniqueGradient and representation optimization
Abstract通过去噪中间概率反馈动态调节残差流转向，证明扩散语言模型在推理服务栈中存在闭环偏见注入脆弱性。
Paper analysisRead analysis
AttacksarXiv 2610.05089Oct 4
研究者披露 LiteLLM 网关跨租户干扰攻击 Cooldown Landmines
提出利用共享冷却的跨租户干扰攻击，并设计租户隔离机制
arXiv
2610.05089
Published
Oct 4
Layer
Infrastructure layer
Setting
LLM applications
- DefensesInstruction–data separation
- AttacksDenial of service
Abstract揭示网关共享冷却漏洞，提出来源检查与租户隔离防御。
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
AttacksarXiv 2610.04195Oct 3
MemLeak research: multi-tenant agents sharing vector memory stores have cross-user memory leakage
提出 MemLeak，评估多租户 Agent 共享向量记忆的跨用户泄露
arXiv
2610.04195
Published
Oct 3
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemini 2.5 Flash, Claude Sonnet 4.5, all-MiniLM-L6-v2 and others5
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Paper analysisRead analysis
AttacksarXiv 2609.35576Sep 29
研究提出跨 LLM 助手的记忆跳跃攻击
提出跨独立 Agent 的记忆跳跃攻击，经共享工件在助手间自传播
arXiv
2609.35576
Published
Sep 29
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-5.6 Luna, Kimi-K2.6, GPT-OSS-120B and others6
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract论文证实持久工件与内存可形成跨智能体传播链，揭示了将共享工件纳入安全防线的重要意义。
该论文系统研究并量化了通过共享持久工件在具有独立私有内存的 LLM 智能体之间发生自传播的“工件介导传播”攻击风险。
Paper analysisRead analysis
AttacksarXiv 2609.33628Sep 27
用课程强化学习对前沿模型做提示注入红队测试
用跨目标课程强化学习训练提示注入红队，攻破前沿智能体
arXiv
2609.33628
Published
Sep 27
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-4o-mini, GPT-5-nano, GPT-5.6-Luna and others12
- AttacksPrompt injection
- TechniqueAutomated search
Abstract提出跨目标模型课程强化学习，攻破前沿模型冷启动瓶颈并实现跨模型迁移。
该研究针对强化学习自动化提示注入红队在攻击前沿大模型时的冷启动问题，提出了一种基于目标模型鲁棒性递进的课程强化学习方法。
Paper analysisRead analysis
AttacksarXiv 2609.22510Sep 19
特拉维夫大学提出爆炸性提示词：条件触发的间接提示注入可绕过九款生产 Agent
提出条件触发的爆炸提示词，并设计摄入期检测器 DeFuse
arXiv
2609.22510
Published
Sep 19
Layer
Application layer
Setting
AI Agent
Evaluated models
Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Qwen2.5-32B-Instruct and others15
- DefensesDetection and filtering
- AttacksPrompt injection
- TechniqueDormant triggers
- ComponentGuardrails and judges
Abstract论文揭示了条件触发使提示注入绕过防御并在触发时执行工具，提出轻量检测器并在摄入期有效防范。
论文针对大语言模型智能体面临的间接提示注入威胁，研究了利用条件句式实现时间分离的爆炸提示词。
Paper analysisRead analysis
AttacksarXiv 2609.06749Sep 7
PMA 攻击：针对隐私保护 LLM 中嵌入到嵌入混淆的语义流形对齐方法
提出 PMA，用流形对齐从 E2EO 混淆向量恢复明文
arXiv
2609.06749
Published
Sep 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
BERT-base, RoBERTa-base, T5-base and others6
- AttacksExtraction and theft
- ComponentEmbeddings
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
AttacksarXiv 2608.17485Aug 18
KeyPooling: Measuring where LLM API relay paths break prompt cache isolation
Proposing KeyPooling to measure where API relays break prompt cache isolation
arXiv
2608.17485
Published
Aug 18
Layer
Infrastructure layer
Setting
Models and APIs
Evaluated models
grok-4-fast-non-reasoning, grok-4-1-fast-non-reasoning, grok-3 and others11
- AttacksExtraction and theft
- TechniqueSide channels
AbstractShared upstream credentials place relay customers in the same cache domain; preserving identity or separate principals can separate them.
KeyPooling measures where LLM API relays drop customer identity, causing prompt caches to no longer be isolated per downstream customer.
Paper analysisRead analysis
AttacksarXiv 2608.05563Aug 6
研究者提出 PoisonedEvolution 轨迹投毒攻击
提出 PoisonedEvolution 轨迹投毒，诱导自演化技能系统固化恶意行为
arXiv
2608.05563
Published
Aug 6
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-5.4, MiniMax-M2.5, DeepSeek-V3.2 and others6
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract论文揭示自演化技能系统的证据晋升漏洞，提出并验证轨迹投毒攻击。
这篇论文揭示了自演化技能系统在将交互经验转化为持久指令时的安全风险。
Paper analysisRead analysis
AttacksarXiv 2608.05108Aug 6
PIMiner：无需再训练即可跨模型迁移的提示注入红队智能体系统
提出 PIMiner，用可复用策略库自动搜索并迁移针对智能体的提示注入
arXiv
2608.05108
Published
Aug 6
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemini-2.5-Pro, DeepSeek-V4-Pro, GPT-4o-mini and others10
- AttacksPrompt injection
- TechniqueAutomated search
Paper analysisRead analysis
AttacksarXiv 2608.04741Aug 5
LoginTrap：针对 LLM Web Agent 的任务无关钓鱼式间接提示注入攻击
提出 LoginTrap，以网页弹窗诱导 Web Agent 提交敏感信息
arXiv
2608.04741
Published
Aug 5
Layer
Application layer
Setting
web agent
Evaluated models
GPT-4o, Gemini 3 Flash, Claude Sonnet 4 and others7
- AttacksPrompt injection
- TechniqueAutomated search
Abstract揭示网络智能体在黑盒网页下的登录诱导风险，利用模糊测试生成话术并跨骨干和架构验证了隐私泄露威胁。
Paper analysisRead analysis

AI Safety Daily

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

All papers

Attack type

Attack technique

Impact

System type

Attacker access

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

An exploration of attacks on AI agent systems

研究：LLM 路由决策日志可推断用户医疗、自伤等敏感话题

WebMirage hijacks visual web agents' browser operations with adversarial images

ASPIRE：面向 LLM Agent 的开放式提示注入红队引擎

SkillPoison：用成功经验投毒自进化 Agent 的技能形成

TranScope：利用 CPU 性能计数器对 Transformer 做成员推断攻击

研究者提出闭环偏见注入攻击

研究者披露 LiteLLM 网关跨租户干扰攻击 Cooldown Landmines

StegoMemory red team testing: agent persistent memory can be used as a cross-session covert channel

MemLeak research: multi-tenant agents sharing vector memory stores have cross-user memory leakage

研究提出跨 LLM 助手的记忆跳跃攻击

用课程强化学习对前沿模型做提示注入红队测试

特拉维夫大学提出爆炸性提示词：条件触发的间接提示注入可绕过九款生产 Agent

PMA 攻击：针对隐私保护 LLM 中嵌入到嵌入混淆的语义流形对齐方法

Researchers propose context privilege escalation attack, affecting 12 agent frameworks

KeyPooling: Measuring where LLM API relay paths break prompt cache isolation

研究者提出 PoisonedEvolution 轨迹投毒攻击

PIMiner：无需再训练即可跨模型迁移的提示注入红队智能体系统

LoginTrap：针对 LLM Web Agent 的任务无关钓鱼式间接提示注入攻击