Skip to content

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

Oct 12 · Monday

All papers

Found 18 papers
Filter3

Attack type

Poisoning and backdoors18

Attack technique

Automated search13Multi-turn escalation0Encoding and obfuscation5Defense-targeted7Dormant triggers18Selection manipulation9

Impact

Unauthorized actions6Data and privacy leaks4Output manipulation4

System type

Models and APIs8AI Agent10coding agent4

Attack surface / entry point

User input46Web pages and interfaces4Documents and messages8Tool responses9Tool and skill descriptions7Code repositories and dependencies5Retrieval corpus4Memory writes18Images, audio and video13Training data15Weights and gradients16Distribution channels18

Layer

Application layer7Training and data layer9

System component

MCP and skills5Fine-tuning and open weights11Multimodal3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack technique：Multi-turn escalationAttack technique：Dormant triggersAttack surface / entry point：Distribution channelsClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.13928

    AI models can provably hide arbitrary capabilities

    Proposes digital lock compilation, encrypting executable networks into host weights to hide arbitrary capabilities

    arXiv
    2610.13928
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemma 3 270M
    AbstractThe authors use a digital lock to hide an executable capability and state that elicitation on the chemistry and parity tasks did not recover the capability.

    The authors construct a class of backdoors that encrypt an executable network into the weights, used to discuss the limits of white-box elicitation audits under supply chain attacks.

    Paper analysisRead analysis
  2. AttacksarXiv 2610.09819

    FAB 攻击：给 HuBERT/WavLM 植入后门，背景警笛声即可让下游语音任务失灵

    提出 FAB 攻击，向声学基础模型植入可由环境声触发的后门

    arXiv
    2610.09819
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    HuBERT-base, WavLM-base

    Abstract论文提出了针对声学基模的 FAB 后门攻击，在弱威胁模型下实现了任务无关、物理可触发的后门植入。

    Paper analysisRead analysis
  3. AttacksarXiv 2610.07510

    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
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-Coder-3B-Instruct, Qwen2.5-Coder-7B-Instruct, Qwen3-Coder-30B-A3B-Instruct
    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
  4. AttacksarXiv 2610.06049

    研究者提出仅修改 SAE 解码器的后门攻击，可在不改动语言模型的情况下植入行为

    提出只改 SAE 解码器的后门，在冻结语言模型上植入代码插入

    arXiv
    2610.06049
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemma 3 4B Instruct, Qwen3 1.7B, Llama 3.1 8B Instruct
    Abstract只改解码器的 SAE 可带上代码插入后门，且若干常规质量指标变化不大。

    只改 SAE 解码器、冻结编码器与语言模型，即可把代码插入行为放进推理时的辅助组件。作者把这视为 SAE 供应链问题：checkpoint 一旦替换某一层激活，就参与后续计算，而不只是解释工具。

    Paper analysisRead analysis
  5. AttacksarXiv 2610.05453

    研究者提出 Privacy-Leaking Watermarks，可在本地多模态模型中泄露对话隐私

    提出 PLW，用微调把先前对话敏感触发编码进后续生成图像

    arXiv
    2610.05453
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    OmniGen2, BAGEL-7B

    AbstractPLW 把先前对话线索写成后续图像中的隐水印，检出随触发、模型和间隔变化。

    Paper analysisRead analysis
  8. AttacksarXiv 2609.33569

    信息黑洞：3D 点云重建中的后门机制研究

    提出 Information Blackhole 与 AGM，控制点云自编码器后门重建到指定形状

    arXiv
    2609.33569
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    FoldingNet, PointDiffusion
    AbstractAGM 用自适应高斯匹配压制 PCAE 投毒潜码中的源几何，九组设置的 CD-ASD 均下降。

    这篇工作研究点云自编码器的训练时后门：干净输入仍自重建，带触发的输入应重建成攻击者指定形状。分类后门只需把预测推向离散标签。PCAE 把源几何与目标信息编进同一个连续潜空间，残留源几何会把重建拉回源形状。

    Paper analysisRead analysis
  9. AttacksarXiv 2609.37468

    论文提出针对 Agentic RAG 的检索器后门攻击与 DOU 隐藏方法

    提出检索器后门攻击操纵智能体搜索，并用 DOU 逃避检测

    arXiv
    2609.37468
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    E5, Contriever-MSMARCO

    Abstract论文展示了通过恶意检索器操纵智能体多轮搜索并利用诱饵重塑表征隐蔽后门的可行性与系统风险。

    Paper analysisRead analysis
  10. AttacksarXiv 2609.14060

    AgentQ：针对 LLM Agent 的量化条件后门攻击

    提出量化条件后门 AGENTQ，使智能体仅在量化后触发恶意工具调用

    arXiv
    2609.14060
    Published
    Layer
    Training and data layer
    Setting
    AI Agent
    Evaluated models
    Qwen3.5-2B, Qwen3.5-4B, Qwen3.5-9B and others6

    Abstract论文研究了智能体量化条件后门风险，提出 AGENTQ 在保持效用的同时实现全精度隐蔽与量化后生效。

    Paper analysisRead analysis
  11. AttacksarXiv 2609.07051

    TrojanWorld：通过想象引导对世界模型智能体植入后门

    提出 TrojanWorld，用物理触发器对世界模型智能体植入想象引导后门

    arXiv
    2609.07051
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    TD-MPC2, DreamerV3, R2-Dreamer

    AbstractTrojanWorld 揭示了世界模型智能体的供应链后门风险，通过在世界模型中操纵想象可实现对闭环动作的持续控制。

    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 2608.09577

    ElasticBack：通过触发词与规则耦合在 LLM Agent 技能中植入条件后门

    提出 ElasticBack，在单个 Agent 技能中植入条件后门

    arXiv
    2608.09577
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GLM-5.2, MiniMax-M3, GPT-5.4 and others4
    AbstractElasticBack 用冻结规则加遗传搜索演化 trigger，在单 skill 上做条件后门。

    ElasticBack 是放在 LLM agent 单个 skill 里的条件后门攻击。。

    Paper analysisRead analysis
  15. AttacksarXiv 2608.06862

    SynChain：诱导计算机使用 Agent 自建攻击链并跨任务持久化

    提出 SYNCHAIN，诱导计算机使用 Agent 自建跨任务持久攻击链

    arXiv
    2608.06862
    Published
    Layer
    Application layer
    Setting
    Browser and computer use, coding agent
    Evaluated models
    Qwen3.5-9B, Llama-3.1-8B, Ministral-3-8B

    Abstract论文揭示了 CUA 自合成工件带来的内部供应链威胁，验证了潜伏载荷的跨任务传播能力与防御局限。

    Paper analysisRead analysis
  16. AttacksarXiv 2604.03890

    From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems

    Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA

    arXiv
    2604.03890
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics, LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4

    Abstract推理层后门传不到执行。

    Paper analysisRead analysis
  17. AttacksarXiv 2604.00627

    When Safe Models Become Dangerous: Exploiting Potential Vulnerabilities in LLM Merging

    提出 TrojanMerge，在源模型植入仅在合并后生效的潜伏分量

    arXiv
    2604.00627
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama 2 M1 (safety-aligned chat variant), Tulu-2-7b, Llama 3 M1 (safety-aligned chat variant) and others9
    Paper analysisRead analysis
You have reached the end