Skip to content

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

Oct 12 · Monday

All papers

Found 15 papers
Filter2

Attack type

Prompt injection4Detection evasion3

Defense type

Detection and filtering4

Impact

Harmful content17Unauthorized actions7Data and privacy leaks4Output manipulation15Availability and reliability4Oversight failure9

System type

Models and APIs6LLM applications7

Attack surface / entry point

User input5

Layer

Prompt layer7Application layer7

System component

Memory8RAG5Guardrails and judges15Vision17Audio3Video5Image generation3Multimodal24
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Impact：Output manipulationSystem component：Guardrails and judgesClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.11112

    EpiReal-Bench：商用图像生成模型虚假声明红队基准

    构建 EpiReal-Bench，评测图像生成器将虚假主张渲染为可信证据

    arXiv
    2610.11112
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-Image-2, Nano Banana 2, Grok Imagen 2.0 and others4
    Abstract四款商用图像模型能把假主张画成可信证据。

    EpiReal-Bench 用来量商用图像生成器会不会把虚假现实主张画成可信视觉证据。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2610.07939

    CCDF dataset: Grok Imagine, Veo 3.1, Sora 2 forge surveillance footage, ten deepfake detectors basically cannot recognize it

    提出监控深伪基准 CCDF，在统一编码后评测检测器对伪造犯罪事故录像的识别

    arXiv
    2610.07939
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    C2P-CLIP, ForgeLens, D3-Im and others10

    Abstract提出消除格式捷径的监控深度伪造基准 CCDF，揭示现有检测器难以识别商用生成视频。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2610.02586

    Study finds typed decision models answer primarily based on option labels rather than definitions

    揭示类型化决策模型按选项标签而非定义规则作答

    arXiv
    2610.02586
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    laya-typed-decisions, laya, laya-multilingual and others9

    Abstract揭示类型化决策模型被标签误导的机理，证实源于提示词渲染并给出实操建议。

    Paper analysisRead analysis
  4. 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
  5. Evaluation and benchmarksarXiv 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
  6. Evaluation and benchmarksarXiv 2609.05843

    SinoGlyphBench：中文字形混淆下语言模型审核的诊断基准

    提出 SinoGlyphBench，用配对字形混淆诊断中文审核稳定性

    arXiv
    2609.05843
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-5.4 mini, GPT-5.5, DeepSeek V4 Flash and others12
    AbstractSinoGlyphBench 显示中文字形混淆会同时增加有害漏报和误报，全文扰动最重。

    SinoGlyphBench是一个配对诊断基准，用来看内容审核在可还原的中文字形混淆下是否还保持原决定。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2609.02316

    Counter-GEO-Bench：现有护栏难挡 GEO 虚假信息

    构建 COUNTER-GEO-BENCH，评测生成式搜索中的 GEO 虚假信息防御

    arXiv
    2609.02316
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Gemma-4-31B-IT, Qwen-3.5-35B-A3B, Llama-4-Scout-17B-16E and others8

    Abstract论文构建了针对 GEO 虚假信息的首个防御基准，揭示通用护栏的失效与反作用，并提出了有效的轻量对比检测基线。

    Paper analysisRead analysis
  8. Evaluation and benchmarksarXiv 2608.16824

    GEO-Flag：检测与测量面向生成式引擎优化的网页内容

    提出 GEOFlagBench 与 IPT，检测并测量生成式引擎优化网页

    arXiv
    2608.16824
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    ModernBERT-base, Qwen3-0.6B, Gemini-3.5-flash and others11
    AbstractGEOFlagBench 与 IPT 用于检测 GEO 页，并估计真实检索中的占比与引用可核验性。

    GEO-Flag 把页面级 GEO 检测做成可评测任务，并在发布的检索结果上估计被判为 GEO 的页面占比。

    Paper analysisRead analysis
  9. Evaluation and benchmarksarXiv 2607.14493

    LogInject 框架披露 LLM 日志分析中的被动提示注入

    提出 LogInject 框架，评测日志分析中的被动提示注入及缓解

    arXiv
    2607.14493
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    GPT-4o, Claude 3.5 Sonnet, Llama-3-70B-Instruct

    Abstract论文评估了 LLM 日志分析中的上下文污染风险，提出分片拼接等攻击与三层防御，指出必须结合架构隔离与人工介入。

    Paper analysisRead analysis
  10. Evaluation and benchmarksarXiv 2606.24115

    Gut-VLM 基准：九种幻觉检测方法在胃肠道内镜 VLM 上的评测

    在 Gut-VLM 上评测内镜 VLM 的幻觉检测方法

    arXiv
    2606.24115
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    MedGemma-4B, MedGemma-27B, LLaVA-Med-7B and others5
    Abstract九种检测方法在 Gut-VLM 五模型上的比较中，ReXTrust 的 AUC 均为最高。

    这是一个胃肠道内镜 VQA 幻觉检测的比较基准，不是新检测器结构的提出。

    Paper analysisRead analysis
  12. Evaluation and benchmarksarXiv 2603.05399

    研究者发布 Judge Reliability Harness，压力测试 LLM 评委可靠性

    提出 JRH，压力测试 LLM 评委打分可靠性

    arXiv
    2603.05399
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    GPT-4o, Claude Sonnet 4.5, Claude Opus 4.5 and others5
    AbstractJRH 用合成扰动测四名法官。

    Judge Reliability Harness（JRH）是一套为 LLM 法官生成验证套件的开源库，用来看打分配置在输入变化下是否还跟得上目标标签。

    Paper analysisRead analysis
You have reached the end