Congzheng Song

is this you? claim profile

0 followers
Emory University ∙ cornell university

Adversarial Semantic Collisions

We study semantic collisions: texts that are semantically unrelated but ...
11/09/2020 ∙ by Congzheng Song, et al. ∙ 0 ∙ share

read it
You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion

Code autocompletion is an integral feature of modern code editors and ID...
07/05/2020 ∙ by Roei Schuster, et al. ∙ 0 ∙ share

read it
Information Leakage in Embedding Models

Embeddings are functions that map raw input data to low-dimensional vect...
03/31/2020 ∙ by Congzheng Song, et al. ∙ 0 ∙ share

read it
Generalized Zero-shot ICD Coding

The International Classification of Diseases (ICD) is a list of classifi...
09/28/2019 ∙ by Congzheng Song, et al. ∙ 0 ∙ share

read it
Membership Encoding for Deep Learning

Machine learning as a service (MLaaS), and algorithm marketplaces are on...
09/27/2019 ∙ by Congzheng Song, et al. ∙ 0 ∙ share

read it
Overlearning Reveals Sensitive Attributes

`Overlearning' means that a model trained for a seemingly simple objecti...
05/28/2019 ∙ by Congzheng Song, et al. ∙ 0 ∙ share

read it
The Natural Auditor: How To Tell If Someone Used Your Words To Train Their Model

To help enforce data-protection regulations such as GDPR and detect unau...
11/01/2018 ∙ by Congzheng Song, et al. ∙ 6 ∙ share

read it
Inference Attacks Against Collaborative Learning

Collaborative machine learning and related techniques such as distribute...
05/10/2018 ∙ by Luca Melis, et al. ∙ 0 ∙ share

read it
Chiron: Privacy-preserving Machine Learning as a Service

Major cloud operators offer machine learning (ML) as a service, enabling...
03/15/2018 ∙ by Tyler Hunt, et al. ∙ 0 ∙ share

read it
Fooling OCR Systems with Adversarial Text Images

We demonstrate that state-of-the-art optical character recognition (OCR)...
02/15/2018 ∙ by Congzheng Song, et al. ∙ 0 ∙ share

read it
Kernel Distillation for Gaussian Processes

Gaussian processes (GPs) are flexible models that can capture complex st...
01/31/2018 ∙ by Congzheng Song, et al. ∙ 0 ∙ share

read it
Membership Inference Attacks against Machine Learning Models

We quantitatively investigate how machine learning models leak informati...
10/18/2016 ∙ by Reza Shokri, et al. ∙ 0 ∙ share

read it
Learning Genomic Representations to Predict Clinical Outcomes in Cancer

Genomics are rapidly transforming medical practice and basic biomedical ...
09/27/2016 ∙ by Safoora Yousefi, et al. ∙ 0 ∙ share

read it

Congzheng Song

Featured Co-authors

Alexander M. Rush

Eric Xing

Pengtao Xie

Emiliano De Cristofaro

Shanghang Zhang

Reza Shokri

Vitaly Shmatikov

Yiming Sun

Nelson Nauata

Roei Schuster

Najmeh Sadoughi

Adversarial Semantic Collisions

You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion

Information Leakage in Embedding Models

Generalized Zero-shot ICD Coding

Membership Encoding for Deep Learning

Overlearning Reveals Sensitive Attributes

The Natural Auditor: How To Tell If Someone Used Your Words To Train Their Model

Inference Attacks Against Collaborative Learning

Chiron: Privacy-preserving Machine Learning as a Service

Fooling OCR Systems with Adversarial Text Images

Kernel Distillation for Gaussian Processes

Membership Inference Attacks against Machine Learning Models

Learning Genomic Representations to Predict Clinical Outcomes in Cancer