Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter6

Attack type

Jailbreaks39Prompt injection60Poisoning and backdoors52Extraction and theft5Detection evasion10Malicious use3

System type

Models and APIs3AI Agent0

Attack surface / entry point

Images, audio and video3

System component

Memory0Monitors6Vision3Image generation6Embeddings0Multimodal10
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 useSystem type：Models and APIsSystem type：AI AgentSystem component：MemorySystem component：VisionSystem component：EmbeddingsClear all

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

  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. 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