Kevin Eykholt  Kevin Eykholt photo         

contact information

Researcher
Thomas J. Watson Research Center, Yorktown Heights, NY USA
  

links



2023

URET: Universal Robustness Evaluation Toolkit (for Evasion)
Kevin Eykholt, Taesung Lee, Douglas Schales, Jiyong Jang, Ian Molloy, and Masha Zorin
USENIX Security Symposium, 2023
Abstract


2022

Benchmarking the Effect of Poisoning Defenses on the Security and Bias of the Final Model
Nathalie Baracaldo Angel, Kevin Eykholt, Farhan Ahmed, Yi Zhou, Shriti Priya, Taesung Lee, Swanand Ravindra Kadhe, Mike Tan, Sridevi Polavaram, Sterling Suggs, Yuyang Gao, and David Slater
Trustworthy and Socially Responsible Machine Learning Workshop at NeurIPS, 2022
Abstract

On the Feasibility of Compressing Certifiably Robust Neural Networks
Pratik Vaishnavi, Kevin Eykholt, and Amir Rahmati
Trustworthy and Socially Responsible Machine Learning Workshop at NeurIPS, 2022
Abstract

Accelerating Certified Robustness Training via Knowledge Transfer
Pratik Vaishnavi, Kevin Eykholt, and Amir Rahmati
Annual Conference on Neural Information Processing Systems (NeurIPS, 2022
Abstract

Ares: A System-Oriented Wargame Framework for Adversarial ML
Farhan Ahmed, Pratik Vaishnavi, Kevin Eykholt, and Amir Rahmati
Deep Learning and Security Workshop, 2022
Abstract

Transferring Adversarial Robustness Through Robust Representation Matching
Pratik Vaishnavi, Kevin Eykholt, and Amir Rahmati
31st USENIX Security Symposium, 2022
Abstract


2021

Adaptive Verifiable Training Using Pairwise Class Similarity
Shiqi Wang, Kevin Eykholt, Taesung Lee, Jiyong Jang, Ian Molloy
AAAI Conference on Artificial Intelligence (AAAI), 2021

Separation of Powers in Federated Learning
Pau-Chen Cheng, Kevin Eykholt, Zhongshu Gu, Hani Jamjoom, K. R. Jayaram, Enriquillo Valdez, Ashish Verma
arXiv: Cryptography and Security, 2021
Abstract   news aggregator, information leakage, key, distributed computing, computer science, process, architecture, separation of powers, federated learning, trustworthiness


2020

Can Attention Masks Improve Adversarial Robustness
Pratik Vaishnavi, Tianji Cong, Kevin Eykholt, Atul Prakash, Amir Rahmati
Workshop on Engineering Dependable and Secure Machine Learning Systems, 2020
Abstract


2019

Transferable Adversarial Robustness using Adversarially Trained Autoencoders
Pratik Vaishnavi, Kevin Eykholt, Atul Prakash, Amir Rahmati
arXiv preprint arXiv:1909.05921, 2019
Abstract

Robust Classification using Robust Feature Augmentation
Kevin Eykholt, Swati Gupta, Atul Prakash, Haizhong Zheng
arXiv preprint arXiv:1905.10904, 2019
Abstract


2018

Physical Adversarial Examples for Object Detectors
Kevin Eykholt, Ivan Etimov, Earlence Fernandes, Bo Li, Amir Rahmati, Florian Tramer, Atul Prakash, Tadayoshi Kohno, Dawn Song
Workshop on Offensive Technologies, 2018
Abstract

Tyche: A Risk-Based Permission Model for Smart Homes
Amir Rahmati, Earlence Fernandes, Kevin Eykholt, Atul Prakash
2018 IEEE Cybersecurity Development (SecDev), pp. 29-36
Abstract

Robust Physical-World Attacks on Deep Learning Visual Classification
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Amir Rahmati, Chaowei Xiao, Atul Prakash, Tadayoshi Kohno, Dawn Song
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1625-1634
Abstract


2017

Heimdall: A Privacy-Respecting Implicit Preference Collection Framework
Amir Rahmati, Earlence Fernandes, Kevin Eykholt, Xinheng Chen, Atul Prakash
Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services, pp. 453-463, 2017
Abstract

Ensuring Authorized Updates in Multi-user Database-Backed Applications
Kevin Eykholt, Atul Prakash, Barzan Mozafari
26th {USENIX} Security Symposium ({USENIX} Security 17), pp. 1445-1462, 2017

Internet of Things Security Research: A Rehash of Old Ideas or New Intellectual Challenges?
Earlence Fernandes, Amir Rahmati, Kevin Eykholt, Atul Prakash
IEEE Security & Privacy (S&P Magazine): Systems Attacks and Defenses, pp. 79-84, 2017
Abstract


2013

A Matlab toolbox for visualization of image manifolds
Kevin Eykholt, Marco F. Duarte
2013 IEEE Global Conference on Signal and Information Processing, pp. 633-633
Abstract