Skip to content

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

Oct 13 · Tuesday

All papers

Found 6 papers
Filter4

Attack type

Jailbreaks68Prompt injection145Poisoning and backdoors55Extraction and theft6Detection evasion30Malicious use9

Impact

Data and privacy leaks4

System type

Models and APIs4

Attack surface / entry point

User input54Tool responses0Retrieval corpus3Memory writes1Inter-agent messages3Images, audio and video5Training data7Weights and gradients11Inference services and hardware9

System component

Multimodal4
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：Extraction and theftAttack surface / entry point：Tool responsesAttack surface / entry point：Memory writesAttack surface / entry point：Images, audio and videoClear all

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

  2. Analysis and theoryarXiv 2609.33898

    研究揭示训练效率与模型脆弱性的权衡：高效训练更易受对抗与隐私攻击

    比较高效与高成本训练的对抗和隐私脆弱性并分析损失几何

    arXiv
    2609.33898
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    ResNet-18, Swin Transformer, Qwen2.5-Math-7B-Instruct and others7
    Abstract效用匹配下，三种高效训练都伴随更高的隐私与对抗脆弱性及更尖的损失几何。

    作者在视觉分类和数学推理语言模型上，检查用更少数据或更简对齐换取训练效率时，安全性质是否一起变化。比较在任务效用接近的前提下进行。视觉侧用 KNN-Shapley 的高重要性小子集对照低重要性大子集，并用预训练微调对照从头训练。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.33481

    IDUnlearn-Bench：面向视觉语言模型的个体级遗忘基准

    提出 IDUnlearn-Bench，评测 VLM 个体级遗忘后的身份残留

    arXiv
    2609.33481
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-VL-2B, Qwen3-VL-4B, Qwen3-VL-8B and others6
    AbstractIDUnlearn-Bench 用四族探针显示：压低直接属性访问后，身份仍常能被反向查出、绑定或重构。

    IDUnlearn-Bench 评测 VLM 是否忘掉一个可跨模态识别的人，而不只是答不出某条监督事实。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.23586

    VidMark：面向视频生成模型知识产权保护的高效水印方案

    提出 VidMark 水印方案，核验视频生成模型的输出来源与所有权

    arXiv
    2609.23586
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Stable Video Diffusion (SVD), Open-Sora, Wan
    AbstractVidMark 加解码器引导微调，把模型签名写入 VGM 输出并用于两项核验。

    Huang 等人提出一套面向视频生成模型的生成内嵌水印方案，用来同时判断一条视频是否来自受保护模型，以及一个嫌疑模型是否为该模型的拷贝。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2608.03272

    多智能体协同过滤系统的连接性攻击与防御研究

    复现 AgentCF 上的多智能体攻防并刻画连通性作用

    arXiv
    2608.03272
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B, Claude Haiku 4.5, Mixtral 8×7B and others4
    Abstract连通性沿 k 与ρ改变攻防，且用户/物品与早期/稳态需要分开看。

    作者在 AgentCF 上研究连通性如何改变多智能体协同过滤的攻防，复现已有方法而不是提出新载荷。

    Paper analysisRead analysis
  6. AttacksarXiv 2508.06837

    Prometheus：针对文生图扩散模型的免训练提示词窃取攻击

    提出 Prometheus，从展示图反推文生图模型的在售提示词

    arXiv
    2508.06837
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    No-box (offline transfer)
    Evaluated models
    Midjourney, Leonardo.ai, DALL·E and others4
    Abstract训练无关的 proxy 搜索攻击。

    Prometheus 是针对文生图市场 showcase 的训练无关提示词窃取：攻击者看不到在售文本，只用本地开源 proxy 恢复 subject 和 modifier，并希望换 subject 后风格仍在。

    Paper analysisRead analysis
You have reached the end