Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for David Evans

Formalizing and Estimating Distribution Inference Risks

Sep 24, 2021
Anshuman Suri, David Evans

* Shorter version of work available at arXiv:2106.03699 Update: Labelling error for Census[Race], where graphs were mirror-images because of 1-ratio being used instead of the ratio. Comparison with SOTA also updated; conclusions remain unchanged 

  Access Paper or Ask Questions

Incorporating Label Uncertainty in Understanding Adversarial Robustness

Jul 07, 2021
Xiao Zhang, David Evans

* 20 pages, 6 figures, 1 table 

  Access Paper or Ask Questions

Formalizing Distribution Inference Risks

Jun 07, 2021
Anshuman Suri, David Evans

* 6 pages, 2 figures 

  Access Paper or Ask Questions

Stealthy Backdoors as Compression Artifacts

Apr 30, 2021
Yulong Tian, Fnu Suya, Fengyuan Xu, David Evans

* 20 pages, 9 figures, 14 tables 

  Access Paper or Ask Questions

Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces

Mar 24, 2021
Jack Prescott, Xiao Zhang, David Evans

* ICLR 2021 

  Access Paper or Ask Questions

Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory

Nov 03, 2020
Hannah Chen, Yangfeng Ji, David Evans

* EMNLP 2020 (Findings) 

  Access Paper or Ask Questions

Model-Targeted Poisoning Attacks: Provable Convergence and Certified Bounds

Jun 30, 2020
Fnu Suya, Saeed Mahloujifar, David Evans, Yuan Tian

* 21 pages, code available at: 

  Access Paper or Ask Questions

Revisiting Membership Inference Under Realistic Assumptions

Jun 21, 2020
Bargav Jayaraman, Lingxiao Wang, David Evans, Quanquan Gu

  Access Paper or Ask Questions

Pointwise Paraphrase Appraisal is Potentially Problematic

Jun 05, 2020
Hannah Chen, Yangfeng Ji, David Evans

* ACL 2020 Student Research Workshop 

  Access Paper or Ask Questions

Certifying Joint Adversarial Robustness for Model Ensembles

Apr 21, 2020
Mainuddin Ahmad Jonas, David Evans

* Open source code for our implementation and for reproducing our experiments is available at 

  Access Paper or Ask Questions

One Neuron to Fool Them All

Mar 20, 2020
Anshuman Suri, David Evans

  Access Paper or Ask Questions

Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models

Mar 01, 2020
Xiao Zhang, Jinghui Chen, Quanquan Gu, David Evans

* 14 pages, 2 figures, 5 tables, AISTATS final paper reformatted for readability 

  Access Paper or Ask Questions

Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization

Feb 26, 2020
Sicheng Zhu, Xiao Zhang, David Evans

* 18 pages, 6 figures 

  Access Paper or Ask Questions

Advances and Open Problems in Federated Learning

Dec 10, 2019
Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Keith Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konečný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao

  Access Paper or Ask Questions

Efficient Privacy-Preserving Nonconvex Optimization

Oct 30, 2019
Lingxiao Wang, Bargav Jayaraman, David Evans, Quanquan Gu

* 26 pages, 3 figures, 5 tables 

  Access Paper or Ask Questions

Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness

May 29, 2019
Saeed Mahloujifar, Xiao Zhang, Mohammad Mahmoody, David Evans

* 17 pages, 3 figures, 4 tables 

  Access Paper or Ask Questions

When Relaxations Go Bad: "Differentially-Private" Machine Learning

Mar 01, 2019
Bargav Jayaraman, David Evans

  Access Paper or Ask Questions

Context-aware Monitoring in Robotic Surgery

Jan 28, 2019
Mohammad Samin Yasar, David Evans, Homa Alemzadeh

* 7 pages, 7 figures, accepted in ISMR2019 

  Access Paper or Ask Questions

Cost-Sensitive Robustness against Adversarial Examples

Oct 22, 2018
Xiao Zhang, David Evans

* 16 pages, 5 figures, 3 tables 

  Access Paper or Ask Questions

Smoothing and Mapping using Multiple Robots

May 06, 2018
Karthik Paga, Joe Phaneuf, Adam Driscoll, David Evans

* 7 pages, 12 figures 

  Access Paper or Ask Questions

Query-limited Black-box Attacks to Classifiers

Dec 23, 2017
Fnu Suya, Yuan Tian, David Evans, Paolo Papotti

* 5 Pages, 2017 NIPS workshop on machine learning and computer security (12/08/2017-12/09/2017) 

  Access Paper or Ask Questions

Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks

Dec 05, 2017
Weilin Xu, David Evans, Yanjun Qi

* To appear in Network and Distributed Systems Security Symposium (NDSS) 2018 

  Access Paper or Ask Questions

Feature Squeezing Mitigates and Detects Carlini/Wagner Adversarial Examples

May 30, 2017
Weilin Xu, David Evans, Yanjun Qi

  Access Paper or Ask Questions