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

Oct 13 · Tuesday

All papers

Found 11 papers

Filter5

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.

Attack technique：Gradient and representation optimization Attack technique：Encoding and obfuscation Attack technique：Conversation structure manipulation Impact：Data and privacy leaks Impact：Availability and reliability Clear all

Another 215papers 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
Retest and extend prompt injection against AI agents, and use Agent Card deception to manipulate A2A selection
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
AbstractSingle-agent filtering and classification can be bypassed by format or wording, and A2A card selection is also biased toward names and descriptions.
The authors retested prompt injection on their own LangChain, AutoGen, and A2A systems, and modified the Agent Card to see if choices shifted. The abstract states the experiments mainly highlight single-agent weaknesses while extending attacks to multi-agent.
Paper analysisRead analysis
AttacksarXiv 2610.06814Oct 6
TAPDreamer：可跨任务迁移的世界动作模型对抗补丁
TAPDreamer 用公开编码器做固定补丁。
arXiv
2610.06814
Published
Oct 6
Layer
Prompt layer
Setting
Embodied systems and robotics
Evaluated models
FastWAM, DreamWAM-uncond, DreamWAM-joint and others4
- TechniqueGradient and representation optimization
- ComponentVision
Paper analysisRead analysis
AttacksarXiv 2610.06083Oct 5
研究者提出面向深度强化学习的轨迹级可迁移黑盒对抗攻击
提出轨迹级可迁移对抗攻击，降低深度强化学习策略的期望回报
arXiv
2610.06083
Published
Oct 5
Layer
Model layer
Setting
Embodied systems and robotics
Evaluated models
DQN, Double DQN (DDQN)
- TechniqueGradient and representation optimization
Abstract轨迹级后退视界攻击在 CartPole 上比逐步 FGSM 类和 Sign 噪声更压低回报。
这项工作研究 DRL 上的迁移式黑盒观测攻击：受害参数不可访问时，在白盒代理上造扰动再迁移。
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 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
AttacksarXiv 2608.09867Aug 11
Researchers steal proprietary LLM inference chains via cross-model compatibility of encrypted inference blocks
利用加密思维块的跨模型重放，诱导弱模型逐字转写专有推理链
arXiv
2608.09867
Published
Aug 11
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5 and others13
- AttacksExtraction and theft
- TechniqueReasoning-chain manipulation
- ComponentReasoning chains
Abstract论文揭示了客户端加密思维块跨模型互换漏洞，提出了低成本提取方法并给出防御方案。
Paper analysisRead analysis
AttacksarXiv 2604.01039Apr 1
Evaluating and hardening LLM system instructions against encoding attack extraction
Extract system instructions with encoding and structured requests, and harden them by rewriting with CoT
arXiv
2604.01039
Published
Apr 1
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
GPT-4.1-mini, GPT-3.5-turbo, Gemini-2.5-flash and others7
- AttacksExtraction and theft
- TechniqueEncoding and obfuscation
AbstractEncoded requests can elicit system instructions after a direct refusal.
This work evaluates and hardens the confidentiality of LLM system instructions under encoded extraction. The authors are concerned with: when direct extraction has been rejected, whether the model still surrenders protected content when the same request is rewritten as a formatting or encoding task.
Paper analysisRead analysis
AttacksarXiv 2603.11132Mar 12
WebWeaver: Breaking the topology confidentiality of LLM multi-agent systems via covert context inference
Propose WebWeaver, which compromises only a single agent and recovers the multi-agent communication topology from conversation context.
arXiv
2603.11132
Published
Mar 12
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Llama 3.1 8B, Qwen 2.5 7B, Mistral NeMo 12B and others6
- AttacksExtraction and theft
- TechniqueGradient and representation optimization
AbstractWebWeaver infers topology from context.
WebWeaver is an inference attack against the confidentiality of LLM-MAS communication topology: it controls only one arbitrary agent and recovers the full graph from dialogue context, rather than querying agent IDs.
Paper analysisRead analysis
AttacksarXiv 2601.01296Jan 4
Aggressive compression enables LLM weight stealing
提出面向渗出的权重压缩，评估推理服务器权重窃取可行性
arXiv
2601.01296
Published
Jan 4
Layer
Infrastructure layer
Setting
Models and APIs
Attacker
White-box
Evaluated models
Qwen2-1.5B, Qwen2-7B, Qwen2.5-1.5B and others8
- AttacksExtraction and theft
- TechniqueEncoding and obfuscation
Abstract作者用残差量化加微调压缩权重，并称法医水印便宜且微调后仍可解码。
这篇工作把 LLM 权重渗出看成 APT：攻击者已有未加密权重，但必须把完整权重藏进推理 API 的合法输出。作者认为可压缩性是被忽略的因素，因为推理量化要求解压后仍能低开销前向，而偷权重的人可以接受事后微调。
Paper analysisRead analysis
AttacksarXiv 2505.23266May 29, 2025
AdvOF：用对抗物体融合攻击 VLM 驱动的视觉语言导航智能体
提出 AdvOF，生成对抗物体误导视觉语言导航智能体的场景感知
arXiv
2505.23266
Published
May 29, 2025
Layer
Application layer
Setting
Embodied systems and robotics
Attacker
White-box
Evaluated models
Lseg, Clip, ViT-L/16 and others5
- AttacksDetection evasion
- TechniqueGradient and representation optimization
- ComponentVision
AbstractAdvOF 以多视角融合生成对抗物体。
AdvOF 是针对 VLM 驱动 VLN 服务导航的对抗物体攻击。
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

Attack technique

Impact

System type

Attack surface / entry point

Layer

An exploration of attacks on AI agent systems

TAPDreamer：可跨任务迁移的世界动作模型对抗补丁

研究者提出面向深度强化学习的轨迹级可迁移黑盒对抗攻击

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

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

Researchers steal proprietary LLM inference chains via cross-model compatibility of encrypted inference blocks

Evaluating and hardening LLM system instructions against encoding attack extraction

WebWeaver: Breaking the topology confidentiality of LLM multi-agent systems via covert context inference

Aggressive compression enables LLM weight stealing

AdvOF：用对抗物体融合攻击 VLM 驱动的视觉语言导航智能体