Congzheng Song / 宋丛峥

Curriculum Vitae [pdf]


Email: cs2296[at]
Address: 2 W Loop Rd, Bloomberg Center, New York, NY

About Me

Hello! I am a -year Computer Science Ph.D. student at Cornell University (physically located at Cornell Tech) working with Prof. Vitaly Shmatikov. My current research interests are security & privacy issues in machine learning. I completed my bachelor's degree at Emory University, where I worked closely with Prof. Ymir Vigfusson and Prof. Lee Cooper on some fun real world deep learning application projects.

Research Papers

(* indicates equal contribution)

  1. C.Song, V.Shmatikov
    Fooling OCR Systems with Adversarial Text Images [pdf]
    In arXiv preprint, 2018

  2. C.Song*, Y.Sun*
    Kernel Distillation for Gaussian Processes [pdf][code]
    In arXiv preprint, 2018

  3. S.Yousefi, F.Amrollahi, M.Amgad, C.Dong, J.E.Lewis, C.Song, D.A.Gutman, S.H.Halani, J.E.V.Vega, D.J.Brat, L.A.D.Cooper
    Predicting Clinical Outcomes from Large Scale Cancer Genomic Profiles with Deep Survival Models [pdf][code]
    In Scientific Reports 7 (Nature), 2017

  4. C.Song, T.Risternpart, V.Shmatikov
    Machine Learning Models that Remembers Too Much [pdf][code][talk]
    In The ACM Conference on Computer and Communications Security (CCS), Dallas, Texas, 2017

  5. R.Shokri, M.Stronati, C.Song, V.Shmatikov
    Membership Inference Attacks against Machine Learning Models [pdf][code][talk]
    In 38th IEEE Symposium on Security and Privacy (S&P), San Jose, California, 2017

  6. S.Yousefi, C.Song, N.Nauata, L.Cooper
    Learning Genomic Representations to Predict Clinical Outcomes in Cancer [pdf][code]
    In International Conference on Learning Representation Workshop (ICLR), San Juan, Puerto Rico, 2016

last update: