Skip to content

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

Oct 12 · Monday

All papers

Found 52 papers
Filter5

Attack type

Jailbreaks4Prompt injection9Detection evasion15

Attack technique

Gradient and representation optimization18Role-play and persuasion4Cross-modal payloads13Defense-targeted3

Defense type

Detection and filtering3

Impact

Harmful content158Data and privacy leaks12Output manipulation52Availability and reliability6Oversight failure5

System type

Models and APIs50LLM applications4AI Agent4coding agent2web agent0

Attacker access

Black-box5

Attack surface / entry point

User input20Images, audio and video26

Layer

Prompt layer52Model layer79Application layer14Training and data layer42Infrastructure layer4

System component

Guardrails and judges7Vision21Audio3Multimodal27
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Impact：Output manipulationSystem type：Models and APIsSystem type：coding agentSystem type：web agentLayer：Prompt layerClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. Analysis and theoryarXiv 2610.12313

    The study tests the sensitivity of five large-model compliance systems to perturbations of regulatory rules.

    Diagnose whether compliance system rulings change with perturbations to regulatory rules

    arXiv
    2610.12313
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.3-70B-Instruct, Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct and others5
    AbstractAcross five models, many correct verdicts are largely unchanged by deleting or replacing negation rules.

    Use behavioral counterfactuals and activation probes to audit whether compliance rulings rely on the given rules. The authors aim to separate two kinds of seemingly identical correct rulings: those that use the given rules, and those obtained from case surface features or training patterns.

    Paper analysisRead analysis
  2. 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
  5. 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
  6. AttacksarXiv 2610.07323

    ATLAS：用自适应信任域与主动学习搜索潜在对抗样本集

    提出 ATLAS 用水平集估计恢复黑盒分类器的对抗输入集合

    arXiv
    2610.07323
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    LeNet5, ResNet50 (CIFAR-10 standard), ResNet50 (ImageNet standard) and others5
    AbstractATLAS 用主动水平集估计构造黑盒对抗集，作者称其集合比单点攻击更具代表性。

    ATLAS 是一个查询式 black-box 框架，用来构造诱发失败的对抗输入集合，供鲁棒性审计使用。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2610.06496

    论文提出 Intent-Eval 基准，揭示多轮对话中模型混淆已否决意图

    提出 Intent-Eval 基准，测量多轮对话里模型对已否决意图的混淆

    arXiv
    2610.06496
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3.6-27B, Qwen3-8B, Qwen3-4B-Instruct-2507 and others10
    AbstractIntent-Eval 比较澄清、拒绝与修订。

    Intent-Eval 测的是多轮对话里，模型会不会只执行仍生效的要求。用户可以澄清、拒绝或接受变更。被提到后又失效的内容不该进入答案。

    Paper analysisRead analysis
  10. Analysis and theoryarXiv 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
  11. DefensesarXiv 2610.00883

    DeBERTa-ConPara：面向部署的 AI 生成文本检测，推理端 Unicode 归一化提升对抗鲁棒性

    提出推理时 Unicode 归一化的检测器，识别遭字符级扰动的 AI 生成文本

    arXiv
    2610.00883
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    microsoft/deberta-v3-large, deberta-v3-base, bert-large-cased and others4
    Abstract推理时归一化消除两类 Unicode 攻击，训练时归一化则会删掉对抗监督。

    DeBERTa-ConPara 是一个面向部署的 AI 文本检测器：DeBERTa-v3-large 在多数据集原始文本上训练，推理前做确定性 Unicode 归一化，用一个固定阈值面对没有目标域标签的场景。

    Paper analysisRead analysis
  12. Evaluation and benchmarksarXiv 2609.35028

    VEX-Bench：评测 LLM 生成虚假信息的核验复杂度

    提出 VEX-Bench 评测 LLM 生成虚假信息的核查复杂度

    arXiv
    2609.35028
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Claude Sonnet 4.5, Gemini 3.1 Pro, GPT-5.4 and others7
    AbstractVEX-Bench 用筛查时的五维复杂度衡量虚假信息对核查容量的占用，并报告生成与核查的成本差。

    VEX-Bench 把 LLM 虚假信息的风险从“能否生成”改成“筛查时会占用多少核查容量”。

    Paper analysisRead analysis
  17. AttacksarXiv 2609.08236

    研究：内容不变的风格包装可翻转 LLM 安全评判器的判定

    提出内容不变样式包装，翻转安全评审器的判定

    arXiv
    2609.08236
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-4o-mini (gpt4o), GPT-4o-mini (strongreject), DeepSeek-Chat and others7
    Abstract论文揭示特定安全评审器易受保持内容不变的外层包装诱导改变判定，并指出安全评估应将判定稳定性作为重要考量指标。

    这是一项关于大语言模型自动化安全评审系统表面样式脆弱性的评估研究。

    Paper analysisRead analysis
  18. 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
  19. Evaluation and benchmarksarXiv 2609.04859

    MM-IFEval-Pro：面向视觉语言模型的多语言抗攻击指令遵循基准

    提出抗攻击多语言视觉指令遵循基准 MM-IFEval-Pro

    arXiv
    2609.04859
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-VL-8B-Instruct, InternVL3.5-8B, MiniCPM-V4.5 and others5
    AbstractMM-IFEval-Pro 以规则验证评测中英指令遵循与视觉劫持，GRPO 提高两基座平均分。

    MM-IFEval-Pro 是面向 VLM 的中英多模态指令遵循基准，并配有可用规则计算奖励的 GRPO 训练集。

    Paper analysisRead analysis
  20. AttacksarXiv 2609.03247

    研究揭示大语言模型的自发身份认证失败：五款模型的分阶段开发者身份实验

    提出 MIPC 与 CFA，观察模型自拟测验后接受开发者身份

    arXiv
    2609.03247
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    ChatGPT, Claude, Qwen3.7-Plus and others5
    Abstract自拟测验可造成对话层虚假认证，但所测授权边界并未因此改变。

    这项工作把“模型自己出题、自己批改、再宣布身份已核验”定义成对话层认证失败，并与后端提权分开。

    Paper analysisRead analysis
Load more