C
Congzheng Song
Researcher at Cornell University
Publications - 35
Citations - 5748
Congzheng Song is an academic researcher from Cornell University. The author has contributed to research in topics: Deep learning & Inference. The author has an hindex of 16, co-authored 30 publications receiving 3068 citations.
Papers
More filters
Proceedings ArticleDOI
Membership Inference Attacks Against Machine Learning Models
TL;DR: This work quantitatively investigates how machine learning models leak information about the individual data records on which they were trained and empirically evaluates the inference techniques on classification models trained by commercial "machine learning as a service" providers such as Google and Amazon.
Proceedings ArticleDOI
Exploiting Unintended Feature Leakage in Collaborative Learning
TL;DR: In this article, passive and active inference attacks are proposed to exploit the leakage of information about participants' training data in federated learning, where each participant can infer the presence of exact data points and properties that hold only for a subset of the training data and are independent of the properties of the joint model.
Posted Content
Membership Inference Attacks against Machine Learning Models
TL;DR: In this paper, a membership inference attack is proposed to determine if a record was in the training dataset of a black-box machine learning model using a black box access to the model.
Proceedings ArticleDOI
Machine Learning Models that Remember Too Much
TL;DR: A malicious ML provider who supplies model-training code to the data holder, does not observe the training, but then obtains white- or black-box access to the resulting model is considered, to explain how the adversary can extract memorized information from the model.
Journal ArticleDOI
Predicting clinical outcomes from large scale cancer genomic profiles with deep survival models
Safoora Yousefi,Fatemeh Amrollahi,Mohamed Amgad,Chengliang Dong,Joshua E. Lewis,Congzheng Song,David A. Gutman,Sameer H. Halani,José E. Velázquez Vega,Daniel J. Brat,Lee Ad Cooper +10 more
TL;DR: It is illustrated that deep survival models can successfully transfer information across diseases to improve prognostic accuracy and provide an open-source software implementation of this framework called SurvivalNet that enables automatic training, evaluation and interpretation ofDeep survival models.