태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
The goal of privacy-preserving (deep) learning is to train a model while preserving privacy of the training dataset. Typically, it is understood that the trained model should be privacy-preserving (e.g., due to the training algorithm being differentially private).
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
The Privacy Annotated HMDB51 (PA-HMDB51) dataset is a video-based dataset for evaluating pirvacy protection in visual action recognition algorithms. The dataset contains both target task labels (action) and selected privacy attributes (skin color, face, gender, nudity, and relationship) annotated on a per-frame basis. Source: https://github.com/VITA-Group/PA-HMDB51
ConcurrentQA is a textual multi-hop QA benchmark to require concurrent retrieval over multiple data-distributions (i.e. Wikipedia and email data). The dataset follow the exact same schema and design as HotpotQA. The data set is downloadable here: https://github.com/facebookresearch/concurrentqa. It also contains model and result analysis code. This benchmark can also be used to study privacy when reasoning over data distributed in multiple privacy scopes --- i.e. Wikipedia in the public domain and emails in the private domain. The following is a blog post about the benchmark: https://ai.facebook.com/blog/building-systems-to-reason-securely-over-private-data/
Open Dataset: Mobility Scenario FIMU * An open, multidimensional (6 categorical attributes), and synthetic dataset of faked virtual humans generated by an optimization approach applied to a real-life call-detail-records-based anonymized database. * The original database is from a mobile network operator in France (Orange), which collects statistics on the frequency of users on days and union of days through analyzing mobile phone data (i.e., call detail records). The period of the analysis is 7 days from 2017-05-31 to 2017-06-06. * This dataset can be used for classification tasks and for evaluating (locally) differentially private mechanisms on multidimensional data.
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.