David A. Wagner

发表

On the Robustness of Deep K-Nearest Neighbors

David A. Wagner, Chawin Sitawarin, Chawin Sitawarin, 2019, 2019 IEEE Security and Privacy Workshops (SPW).

Towards Characterizing Model Extraction Queries and How to Detect Them

David A. Wagner, Zhanyuan Zhang, Yizheng Chen, 2021 .

Learning Security Classifiers with Verified Global Robustness Properties

Yizheng Chen, Suman Jana, Xiaojing Liao, 2021, CCS.

Towards Evaluating and Understanding the Adversarial Robustness of Random Transformation Defenses

David A. Wagner, Zachary Golan-Strieb, 2021 .

SLIP: Self-supervision meets Language-Image Pre-training pdf

Saining Xie, Alexander Kirillov, Norman Mu, 2021, ECCV.

DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection

Xinyun Chen, David A. Wagner, Yizheng Chen, 2023, ArXiv.

Part-Based Models Improve Adversarial Robustness

Nicholas Carlini, Chawin Sitawarin, David A. Wagner, 2022, ICLR.

REAP: A Large-Scale Realistic Adversarial Patch Benchmark

Jerry Li, Nabeel Hingun, Chawin Sitawarin, 2022, ArXiv.

Model-Agnostic Defense for Lane Detection against Adversarial Attack

David A. Wagner, Henry Xu, An Ju, 2021, Proceedings Third International Workshop on Automotive and Autonomous Vehicle Security.

Clipped BagNet: Defending Against Sticker Attacks with Clipped Bag-of-features

Zhanyuan Zhang, Benson Yuan, Michael McCoyd, 2020, 2020 IEEE Security and Privacy Workshops (SPW).

Minority Reports Defense: Defending Against Adversarial Patches

Michael McCoyd, David Wagner, Steven Chen, 2020, ACNS Workshops.

Minimum-Norm Adversarial Examples on KNN and KNN based Models

Chawin Sitawarin, David Wagner, Chawin Sitawarin, 2020, 2020 IEEE Security and Privacy Workshops (SPW).

Improving Adversarial Robustness Through Progressive Hardening pdf

Supriyo Chakraborty, Chawin Sitawarin, David Wagner, 2020, ArXiv.

Defending against Adversarial Patches with Robust Self-Attention

David A. Wagner, Norman Mu, 2021 .

SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothing

Chawin Sitawarin, David A. Wagner, S. Chakraborty, 2020, AISec@CCS.

SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothing

Chawin Sitawarin, David Wagner, Supriyo Chakraborty, 2020, AISec@CCS.

Demystifying the Adversarial Robustness of Random Transformation Defenses

Chawin Sitawarin, David A. Wagner, Zachary Golan-Strieb, 2022, ICML.

Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks pdf

Trevor Darrell, Evan Shelhamer, David Wagner, 2021, ArXiv.

Continuous Learning for Android Malware Detection

David A. Wagner, Yizheng Chen, Zhoujie Ding, 2023, USENIX Security Symposium.

DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection

Xinyun Chen, David A. Wagner, Yizheng Chen, 2023, ArXiv.

Defending Against Adversarial Examples with K-Nearest Neighbor

Chawin Sitawarin, David A. Wagner, 2019, ArXiv.

MITIGATING ADVERSARIAL TRAINING INSTABILITY

Chawin Sitawarin, David A. Wagner, A. Sridhar, 2021 .

REAP: A Large-Scale Realistic Adversarial Patch Benchmark

Jerry Li, Nabeel Hingun, Chawin Sitawarin, 2022, ArXiv.

Yizheng Chen, David Wagner, Zhanyuan Zhang, 2021, AISec@CCS.

Continuous Learning for Android Malware Detection

David A. Wagner, Yizheng Chen, Zhoujie Ding, 2023, USENIX Security Symposium.

Adversarial Examples for k-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams

Evgenios M. Kornaropoulos, D. Song, Chawin Sitawarin, 2020, NeurIPS.

Improving Adversarial Robustness Through Progressive Hardening

Supriyo Chakraborty, Chawin Sitawarin, David A. Wagner, 2020, ArXiv.