Dong Su

Dong Su

Auto-generated profile, based on publicly available information

Dong Su

Purdue University 305 N. University Street 47907 West Lafayette IN USA

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2019
Verified
Conference Paper
Open access
ZGZhongshu Gu
Zhongshu Gu
HJHani Jamjoom
Hani Jamjoom
DSDong Su
Dong Su
HHHeqing Huang
Heqing Huang
JZJialong Zhang
Jialong Zhang
IMIan Molloy
Ian Molloy
Distributed collaborative learning (DCL) paradigms enable building joint machine learning models from distrusted multi-party participants. Data confidentiality is guaranteed by retaining private training data on each participant's local infrastructure. However, this approach makes today's DCL design fundamentally vulnerable to data poisoning and backdoor attacks. It limits DCL's model accountability, which is key to backtracking problematic training data instances and their responsible contributors. In this paper, we introduce CALTRAIN, a centralized collaborative learning system that simultaneously achieves data confidentiality and model accountability. CALTRAIN enforces isolated computation via secure enclaves on centrally aggregated training data to guarantee data confidentiality. To support building accountable learning models, we securely maintain the links between training instances and their contributors. Our evaluation shows that the models generated by CALTRAIN can achieve the same prediction accuracy when compared to the models trained in non-protected environments. We also demonstrate that when malicious training participants tend to implant backdoors during model training, CALTRAIN can accurately and precisely discover the poisoned or mislabeled training data that lead to the runtime mispredictions.

2 February 2018 in The VLDB Journal
Verified
Journal Article
Closed access
PDF file
DSDong Su
Dong Su
JCJianneng Cao
Jianneng Cao
NLNinghui Li
Ninghui Li
MLMin Lyu
Min Lyu

21 June 2011 in arXiv
Verified
Preprint
Open access
PDF file
NLNinghui Li
Ninghui Li
WQWahbeh Qardaji
Wahbeh Qardaji
DSDong Su
Dong Su
This paper aims at answering the following two questions in privacy-preserving data analysis and publishing: What formal privacy guarantee (if any) does $k$-anonymization provide? How to benefit from the adversary's uncertainty about the data? We have found that random sampling provides a connection that helps answer these two questions, as sampling can create uncertainty. The main result of the paper is that $k$-anonymization, when done "safely", and when preceded with a random sampling step, satisfies $(\epsilon,\delta)$-differential privacy with reasonable parameters. This result illustrates that "hiding in a crowd of $k$" indeed offers some privacy guarantees. This result also suggests an alternative approach to output perturbation for satisfying differential privacy: namely, adding a random sampling step in the beginning and pruning results that are too sensitive to change of a single tuple. Regarding the second question, we provide both positive and negative results. On the positive side, we show that adding a random-sampling pre-processing step to a differentially-private algorithm can greatly amplify the level of privacy protection. Hence, when given a dataset resulted from sampling, one can utilize a much large privacy budget. On the negative side, any privacy notion that takes advantage of the adversary's uncertainty likely does not compose. We discuss what these results imply in practice.