Skip to content

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

Oct 13 · Tuesday

All papers

Found 4 papers
Filter5

Attack type

Jailbreaks7Prompt injection15Poisoning and backdoors35Model tampering4Detection evasion32Malicious use4

Impact

Harmful content6Unauthorized actions3Data and privacy leaks3Output manipulation3Increased misuse capability1

System type

Models and APIs4coding agent0

Attack surface / entry point

User input3

Layer

Prompt layer3
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.
Attack type：Malicious useImpact：Output manipulationImpact：Increased misuse capabilitySystem type：Models and APIsSystem type：coding agentClear all

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

  1. 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
  2. DefensesarXiv 2608.00716

    生成图像更易被遗忘：面向合成图像检测的机器遗忘视角

    提出机器遗忘式生成图像检测，用遗忘前后特征相似度区分自然图与生成图

    arXiv
    2608.00716
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    DINOv2 ViT-S/14, DINOv2 ViT-B/14, DINOv2 ViT-L/14 and others9
    Abstract作者用剪枝或 LoRA 遗忘拉开生成图与自然图的特征相似度，并在多个检测基准上报告结果。

    这篇工作把 AI 生成图像检测写成对预训练视觉模型的机器遗忘：原模型对两类图像损失都低，剪枝后生成图特征变得更不像原模型。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2602.21831

    A multi-turn framework for evaluating AI misuse in fraud and cybercrime scenarios

    提出 LFT 多轮框架，评测模型对欺诈与网络犯罪的可执行协助

    arXiv
    2602.21831
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Claude Sonnet 3.5, Claude Sonnet 3.7, Claude Sonnet 4 and others14
    Abstract作者称低努力文本诱导下，多轮 LFT 中模型对三类犯罪的信息协助有限。

    作者给出一套由执法与政策专家校验的多轮评测，用来估计文本模型经由信息提供，对欺诈和网络犯罪有多少可执行协助。

    Paper analysisRead analysis
  4. AttacksarXiv 2601.12983

    ChartAttack: Testing Large Language Models' Vulnerability to Malicious Prompts in Chart Generation

    提出 ChartAttack，用恶意提示驱动代码模型生成误导图表

    arXiv
    2601.12983
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Claude-4.6-Sonnet, GPT-4o, Gemini-2.5-Flash and others20
    AbstractChartAttack 生成不改数据的误导图，降低 MLLM 与人类的图表问答准确率。

    ChartAttack 研究恶意提示能否让 MLLM 在不改数据的情况下生成误导图表，并量化这些图对其他 MLLM 和人类图表问答的影响。

    Paper analysisRead analysis
You have reached the end