Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter2

Attack type

Detection evasion3

Impact

Output manipulation3

System type

Models and APIs215LLM applications5AI Agent9coding agent3Embodied systems and robotics6

Attack surface / entry point

User input4

Layer

Prompt layer5Model layer5Application layer119

System component

Guardrails and judges5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 305papers have no tags yet and are not included in filtered results.
System type：LLM applicationsLayer：Prompt layerClear all

Another 305papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.37863

    MIST 压力测试：无关图像会扰动 VLM 评判者标签

    提出 MIST 压力测试，检验无关图像是否扰动 VLM 评判者标签

    arXiv
    2609.37863
    Published
    Layer
    Prompt layer
    Setting
    LLM applications
    Evaluated models
    GPT-5.2, Gemini 3.1 Flash-Lite, Gemini 3.5 Flash and others13
    Abstract有图就改标签，图的内容却不告知 judge，裁决绑定配置。

    作者用MIST问：VLM 代替人类标注时，可替代性裁决会不会被指南要求忽略的图像改写。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2609.33401

    论文评估 System One 模型在 Agent 安全决策中的可靠性、校准与选择性自动化

    评测 System One 模型对 Agent 安全输入的分类可靠性与校准

    arXiv
    2609.33401
    Published
    Layer
    Prompt layer
    Setting
    LLM applications
    Evaluated models
    Jev 1.13, Laya, English checkpoint, Decider, approximately 2B and others4
    Abstract离线评测表明，安全判定的总体分数和校准不能代替分组误差和带预算的自动决策检查。

    Liu 离线评测 System One 模型能否为智能体安全输入给出可自动化的概率决策。问题是分类是否可靠，以及概率能否在指定漏检和误拦上限内支持放行、拦截或复核。

    Paper analysisRead analysis
  3. AttacksarXiv 2606.09700

    研究者提出 HPAA 攻击：用排版视觉线索绕过 13 个内容审核系统

    提出 HPAA 攻击，用排版视觉线索绕过内容审核系统

    arXiv
    2606.09700
    Published
    Layer
    Prompt layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    Llama-Guard-3-8B, Perspective API, ShieldGemma-2B and others13
    Abstract揭示了排版视觉线索与分词差异带来的审核盲区，HPAA 以极低查询实现近乎完全规避。

    这篇论文研究了人类视觉感知与大模型分词处理机制之间的差异所导致的内容审核漏洞。

    Paper analysisRead analysis
  4. AttacksarXiv 2605.26156

    BITE：用上下文赌博机操纵风格偏置攻击 LLM 评委

    提出 BITE，用上下文赌博机选择风格修改抬高 LLM 评委打分

    arXiv
    2605.26156
    Published
    Layer
    Prompt layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    o3-mini, Gemini-2.5-Flash, Llama-3.3-70B-Instruct and others8
    AbstractBITE 用黑盒赌博机利用风格偏差抬分，作者称这对 LLM-as-a-judge 构成威胁。

    BITE 是黑盒风格操纵：在保持答案语义的同时，抬高 LLM 评审给出的分数。

    Paper analysisRead analysis
  5. DefensesarXiv 2601.19051

    用 HASTE 主动加固 LLM 防御

    提出 HASTE，挖掘 hard negative 再训练恶意提示检测器

    arXiv
    2601.19051
    Published
    Layer
    Prompt layer
    Setting
    LLM applications
    Evaluated models
    protectai/deberta-v3-base-prompt-injection
    AbstractHASTE 用 hard negative 再训练检测器。

    HASTE 是检测器侧的闭环硬化框架：持续构造能绕过当前检测的对抗提示，再用来更新恶意提示分类器。

    Paper analysisRead analysis
You have reached the end