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 Atul Prakash

Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples


Jul 01, 2021
Nelson Manohar-Alers, Ryan Feng, Sahib Singh, Jiguo Song, Atul Prakash

* ICML 2021 workshop on A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning 

  Access Paper or Ask Questions

Essential Features: Reducing the Attack Surface of Adversarial Perturbations with Robust Content-Aware Image Preprocessing


Dec 03, 2020
Ryan Feng, Wu-chi Feng, Atul Prakash


  Access Paper or Ask Questions

Understanding and Diagnosing Vulnerability under Adversarial Attacks


Jul 17, 2020
Haizhong Zheng, Ziqi Zhang, Honglak Lee, Atul Prakash


  Access Paper or Ask Questions

Towards Robustness against Unsuspicious Adversarial Examples


May 08, 2020
Liang Tong, Minzhe Guo, Atul Prakash, Yevgeniy Vorobeychik

* v1.0 

  Access Paper or Ask Questions

MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation


May 06, 2020
Sanjay Kariyappa, Atul Prakash, Moinuddin Qureshi


  Access Paper or Ask Questions

Query-Efficient Physical Hard-Label Attacks on Deep Learning Visual Classification


Feb 17, 2020
Ryan Feng, Jiefeng Chen, Nelson Manohar, Earlence Fernandes, Somesh Jha, Atul Prakash


  Access Paper or Ask Questions

Efficient Adversarial Training with Transferable Adversarial Examples


Dec 27, 2019
Haizhong Zheng, Ziqi Zhang, Juncheng Gu, Honglak Lee, Atul Prakash


  Access Paper or Ask Questions

Can Attention Masks Improve Adversarial Robustness?


Dec 21, 2019
Pratik Vaishnavi, Tianji Cong, Kevin Eykholt, Atul Prakash, Amir Rahmati

* Version presented at AAAI-20 workshop on Engineering Dependable and Secure Machine Learning Systems (EDSMLS) 

  Access Paper or Ask Questions

Transferable Adversarial Robustness using Adversarially Trained Autoencoders


Sep 12, 2019
Pratik Vaishnavi, Kevin Eykholt, Atul Prakash, Amir Rahmati


  Access Paper or Ask Questions

Robust Classification using Robust Feature Augmentation


May 31, 2019
Kevin Eykholt, Swati Gupta, Atul Prakash, Haizhong Zheng


  Access Paper or Ask Questions

Analyzing the Interpretability Robustness of Self-Explaining Models


May 27, 2019
Haizhong Zheng, Earlence Fernandes, Atul Prakash


  Access Paper or Ask Questions

Designing Adversarially Resilient Classifiers using Resilient Feature Engineering


Dec 17, 2018
Kevin Eykholt, Atul Prakash


  Access Paper or Ask Questions

Physical Adversarial Examples for Object Detectors


Oct 05, 2018
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Amir Rahmati, Florian Tramer, Atul Prakash, Tadayoshi Kohno, Dawn Song

* This paper is the extended version of the USENIX WOOT 2018 version 

  Access Paper or Ask Questions

Note on Attacking Object Detectors with Adversarial Stickers


Jul 23, 2018
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Dawn Song, Tadayoshi Kohno, Amir Rahmati, Atul Prakash, Florian Tramer

* Short Note: The full version of this paper was accepted to USENIX WOOT 2018, and is available at arXiv:1807.07769 

  Access Paper or Ask Questions

Robust Physical-World Attacks on Deep Learning Models


Apr 10, 2018
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Amir Rahmati, Chaowei Xiao, Atul Prakash, Tadayoshi Kohno, Dawn Song

* Accepted to CVPR 2018 

  Access Paper or Ask Questions