Skip to content

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

Oct 13 · Tuesday

All papers

Found 24 papers
Filter5

Attack type

Jailbreaks10Prompt injection10Poisoning and backdoors9

Attack technique

Gradient and representation optimization62Automated search104Multi-turn escalation30Encoding and obfuscation61Role-play and persuasion28Conversation structure manipulation13Reasoning-chain manipulation15Cross-modal payloads57Side channels3Defense-targeted44Dormant triggers60Selection manipulation11

Impact

Harmful content9Unauthorized actions4Data and privacy leaks5Output manipulation5

System type

Models and APIs11LLM applications4AI Agent13coding agent3Multi-agent systems0

Attacker access

Black-box8

Attack surface / entry point

User input14Tool responses3Tool and skill descriptions11Distribution channels9

Layer

Prompt layer9Application layer13

System component

MCP and skills10Reasoning chains5
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：Conversation structure manipulationAttack technique：Selection manipulationSystem type：Models and APIsSystem type：AI AgentSystem type：Multi-agent systemsClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.12644

    Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

    Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.

    arXiv
    2610.12644
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.

    Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.

    Paper analysisRead analysis
  2. AttacksarXiv 2610.12524

    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
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Ollama Mistral 0.9.5, llama3-8b-8192, gemini-2.0-flash-lite and others5
    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
  4. AttacksarXiv 2609.36956

    研究者提出 Controlled Decoding Attacks，通过纯文本接口越狱黑盒 LLM

    提出 BLINDBIAS，通过纯文本续写与前缀控制越狱黑盒模型

    arXiv
    2609.36956
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GLM-5, Gemini-3.5-Flash, Qwen3-32B and others4
    Abstract作者认为，隐藏数值概率并不足以消除支持重复采样和前缀续写的解码攻击面。

    BLINDBIAS 是一种针对 sample-only 续写接口的 black-box 解码时越狱框架，研究没有目标数值概率时，采样能否支持逐步控制。

    Paper analysisRead analysis
  5. AttacksarXiv 2609.30383

    研究者提出技能级联攻击

    提出技能级联攻击，把有害目标拆散到多个技能里绕过单技能扫描

    arXiv
    2609.30383
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, GPT-5.4 Mini, Claude Opus 4.6 and others11

    Abstract论文探讨了多技能智能体系统面临的技能级联攻击风险，提出自动化红队框架与基准集，指出跨技能交互存在安全防护盲区。

    Paper analysisRead analysis
  7. AttacksarXiv 2609.27542

    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
    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

    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
  13. AttacksarXiv 2608.25776

    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
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Devstral-Small-2, Gemma-4-31B-IT, Qwen3-Coder-Next and others7

    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
  14. AttacksarXiv 2608.12273

    研究者提出 Convergent Detour Hijacking 攻击，可让技能型 LLM Agent 绕路并放大资源消耗

    提出 CDH 攻击，让技能型 Agent 绕路放大资源消耗

    arXiv
    2608.12273
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude-Haiku-4.5, DeepSeek-V4-Pro, DeepSeek-V4-Flash and others6
    AbstractCDH 让静态技能在保持任务完成时拉高调用与 token，耗时则因后端而异。

    CDH 是针对渐进披露技能智能体的发布者侧、纯文本攻击：一个静态协调器把本可正确完成的任务，拐进有界但更耗资源的技能绕路，再交还原任务。

    Paper analysisRead analysis
  15. AttacksarXiv 2608.09867

    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
    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

    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
  16. AttacksarXiv 2607.12340

    Research: LLM agent skill-name hallucination rates reach up to 62%, which can be exploited via squatting for supply-chain attacks

    提出技能名称抢注攻击，利用 Agent 虚构技能名实施供应链劫持

    arXiv
    2607.12340
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GLM-4.5-Air, GPT-5.4-mini, Claude Sonnet 4.6 and others12
    Abstract研究证实智能体虚构技能名具有高发生率与可预测性，现有防御难以兼顾安全与效用，亟需注册表结构性防护。

    本研究系统揭示了大模型智能体技能推荐场景下的虚构技能名称安全风险，将其形式化为一种新型供应链抢注攻击。

    Paper analysisRead analysis
  18. AttacksarXiv 2607.00422

    KidnapRAG：黑盒投毒攻击劫持 Agentic RAG 的推理链

    提出 KidnapRAG，用投毒文档黑盒劫持 Agentic RAG 的推理链

    arXiv
    2607.00422
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen2.5-32B-Instruct, Llama-3.3-70B-Instruct, QwQ-32B and others5
    Abstract顺序投毒可把多步推理拖向指定应答，作者称关键在持续引导而非单次注入。

    KidnapRAG 是针对 Agentic RAG 的 black-box 语料投毒：攻击者不能访问模型、提示词、检索器或私有轨迹，只能发布可能被检索的文档，并利用公开界面上的推理与搜索查询。

    Paper analysisRead analysis
  19. Analysis and theoryarXiv 2606.04168

    论文提出随机插入攻击，利用自回归一致性绕过 LLM 安全对齐

    解释自回归一致性如何导致浅层安全对齐，并提出随机插入攻击

    arXiv
    2606.04168
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Abstract作者用自回归一致性串起浅层对齐、插入攻击和最坏延续对齐。

    作者把浅层安全对齐和一类续写攻击都归到自回归一致性上。

    Paper analysisRead analysis
  20. InterpretabilityarXiv 2603.08234

    The Continuation vs. Refusal Debate: Mechanism Analysis of Continuation-Triggered Jailbreaks in Large Language Models

    Analyzing the attention head mechanism of continuation-triggered jailbreaks and proposing HCS

    arXiv
    2603.08234
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LLaMA-2-7B-Chat, Qwen2.5-7B-Instruct
    AbstractThe authors state that jailbreaks arise from competition between two types of heads, and that HCS plus distillation can use this competition for inference-time intervention.

    The authors use attention head mechanism analysis for continuation-triggered jailbreaks: under the same harmful instruction, moving the continuation suffix from after the instruction to outside the prompt boundary makes the model more likely to continue generating along the suffix.

    Paper analysisRead analysis
Load more