Skip to content

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

Oct 13 · Tuesday

All papers

Found 5 papers
Filter5

Impact

Output manipulation5Availability and reliability0

System type

Models and APIs3

Attack surface / entry point

User input37Web pages and interfaces20Documents and messages29Tool responses18Tool and skill descriptions8Code repositories and dependencies6Retrieval corpus28Memory writes9Inter-agent messages10Images, audio and video17Training data6Weights and gradients6Distribution channels15Inference services and hardware5

Layer

Model layer3Application layer2Infrastructure layer4
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.
Impact：Output manipulationImpact：Availability and reliabilityAttack surface / entry point：Inference services and hardwareLayer：Model layerLayer：Application layerClear all

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

  1. AttacksarXiv 2610.05894

    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
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    LLaDA-8B-Instruct, Dream-v0-Instruct-7B, LLaDA-MoE-7B-A1B-Instruct

    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
  2. DefensesarXiv 2610.02349

    MIRROR：面向多智能体通信的法定人数完整性防御

    提出 MIRROR，用多路径摘要多数表决保障多智能体通信完整性

    arXiv
    2610.02349
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Gemma-4-31B-it, Gemini 2.5 Pro
    AbstractMIRROR 靠多数路径。

    MIRROR 是 LLM 多智能体通信层上的多路径法定人数完整性原语，只处理不透明字节，不解释消息内容。要处理的是 Agent-in-the-Middle：中介合法终结 TLS 后可改在途消息，而语义校验有推理开销和误拦，签名又要求私钥管理。做法是生成结束后复制同一规范化载荷。

    Paper analysisRead analysis
  3. AttacksarXiv 2602.17837

    TFL: Targeted Bit-Flip Attack against Large Language Models

    Proposes TFL targeted bit flipping so that selected prompts output false answers while unrelated queries remain correct

    arXiv
    2602.17837
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-8B, DeepSeek-R1-Distill-Qwen-14B, LLaMA-3.1-8B-INSTRUCT
    AbstractTFL searches weight bits on three LLMs to make specified prompts produce target keywords while constraining degradation on unrelated tasks.

    TFL is a framework for targeted bit flips on LLM main memory weights: the attacker wants a selected prompt to output a specified false answer keyword while limiting degradation on unrelated queries.

    Paper analysisRead analysis
  4. DefensesarXiv 2601.21189

    Adaptive robust cost-aware Proof of Quality for decentralized LLM inference networks

    为去中心化 LLM 推理网络提出稳健成本感知 PoQ，抵御恶意评估者操纵分数

    arXiv
    2601.21189
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    llama 3 2 3b, gemma 2 2b it, tinyllama 1 1b and others10
    Abstract成本感知 PoQ 加入稳健共识。

    这篇扩展工作把成本感知 Proof of Quality 的共识层改成能承受恶意评估分数的形式，奖励仍同时看输出质量与延迟成本。

    Paper analysisRead analysis
  5. AttacksarXiv 2601.04261

    针对大语言模型后门指纹的抑制攻击

    提出 TFA 与 SVA，抑制 ensemble 后门指纹验证

    arXiv
    2601.04261
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LLaMA2-7B, LLaMA3.1-8B-It, Qwen2.5-7B and others11
    Abstract两种 ensemble 攻击 TFA/SVA 抑制后门指纹。

    TFA 与 SVA 是针对后门式 LLM 指纹的 ensemble 抑制攻击，不改模型参数。所有者用 SFT 写入秘密对，只通过 API 验证版权。攻击者未授权取得模型，不知道触发和指纹，却要把每个模型的验证变成失败，同时让 ensemble 至少不差于性能最高的单模型。

    Paper analysisRead analysis
You have reached the end