Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter4

Attack type

Poisoning and backdoors6Extraction and theft2Detection evasion3

Defense type

Model hardening3

Impact

Output manipulation3

System type

Models and APIs5

Attack surface / entry point

Images, audio and video4

Layer

Prompt layer5Application layer3Training and data layer5

System component

Fine-tuning and open weights4Vision5Multimodal6
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.
Attack type：Extraction and theftAttack type：Detection evasionLayer：Training and data layerSystem component：VisionClear all

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

  1. 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
  2. DefensesarXiv 2609.15671

    QPriv-VL：面向视觉语言模型的问题引导 token 裁剪隐私防御

    提出 QPriv-VL，用问题引导剪枝降低分布式视觉问答的隐私泄露

    arXiv
    2609.15671
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    LLaVA-1.5-7B, Llama-2
    AbstractQPriv-VL 在切层前按问题相关度与 DINOv2 敏感度剪视觉 token，作者称能在约四成 token 下兼顾准确率与四类攻击。

    QPriv-VL 把问题引导的视觉 token 剪枝做成分布式 VQA 的客户端隐私防御，而不是只做集中式推理加速。

    Paper analysisRead analysis
  3. DefensesarXiv 2608.12876

    SPARED：用对抗编辑数据训练基于推理的 AI 生成图像检测器

    提出 SPARED，用对抗编辑数据训练基于推理的 AI 生成图像检测器

    arXiv
    2608.12876
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Black-box, White-box
    Evaluated models
    Qwen3.5-9B
    AbstractSPARED 用防捷径的编辑对抗环训练 9B 推理检测器。

    SPARED 是一套用于可解释 AI 生成图像检测的攻防强化学习流程，报告模型是 Qwen3.5-9B 上的第三轮防御器。

    Paper analysisRead analysis
  4. DefensesarXiv 2602.18252

    Adversarial robustness of discrete image tokenizers

    提出无监督对抗微调，加固离散图像 tokenizer

    arXiv
    2602.18252
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    UniTok, UniTok-MLLM, TiTok-BL128 and others7
    Abstract无监督嵌入攻击暴露离散 tokenizer 的弱点，只微调 encoder 即可提升多任务鲁棒准确率。

    作者研究离散图像 tokenizer 的对抗鲁棒性，给出与任务无关的嵌入攻击，以及只微调 encoder 的无监督对抗训练。

    Paper analysisRead analysis
  5. DefensesarXiv 2602.12461

    Semantic-aware adversarial fine-tuning for CLIP

    Propose SAFT, which uses semantic description ensembles to construct adversarial examples and fine-tune the image encoder

    arXiv
    2602.12461
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    ViT-B/32, CLIP-L/14
    AbstractSAFT fine-tunes the CLIP image encoder with ensemble adversarial examples from refined class descriptions to improve the trade-off between zero-shot accuracy and robustness.

    SAFT is a method for adversarially fine-tuning the CLIP image encoder to improve the accuracy–robustness trade-off in zero-shot classification.

    Paper analysisRead analysis
You have reached the end