Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Attack type

Poisoning and backdoors3Extraction and theft3

Defense type

Model hardening3

Impact

Data and privacy leaks3

System type

Models and APIs3

Layer

Application layer3Training and data layer3Infrastructure layer0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftLayer：Training and data layerLayer：Infrastructure layerClear all

Another 255papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.40286

    研究者提出 COVER：在语言预算下选择源语言实现跨语言遗忘

    提出 COVER，在语言预算下选择源语言实现跨语言知识遗忘

    arXiv
    2609.40286
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Tiny Aya Global, Qwen3-4B-Instruct-2507, Llama-3.2-3B-Instruct
    AbstractCOVER 在语言预算下选源语言，以降低未监督语言上相对 oracle 的残余访问。

    语言预算下的多语言遗忘：遗忘监督只放在 K 种源语言上，目标是降低其余语言对同一事实的残余访问，而不是把每种评测语言都译成监督数据。

    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
You have reached the end