Publications

Selected Publications 

Adversarial threat vectors and risk mitigation for retrieval-augmented generation systems

CM Ward, J Harguess

2025 SPIE DCS Assurance and Security for AI-enabled Systems 2025 13476, 80-97

Offensive security for AI systems: concepts, practices, and applications

J Harguess, CM Ward

2025 SPIE DCS Assurance and Security for AI-enabled Systems 2025 13476, 98-108

The AI security pyramid of pain

CM Ward, J Harguess, J Tao, D Christman, M Tan, P Spicer

2024 SPIE DCS Assurance and Security for AI-enabled Systems 13054, 44-53

Fake it till you break it: evaluating the performance of synthetically optimized adversarial patches against real-world imagery

M Zarei, CM Ward, J Harguess, M Aiken

2023 SPIE DCS Geospatial Informatics XIII 12525, 172-183

Is the next winter coming for AI? Elements of making secure and robust AI

J Harguess, CM Ward

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), 1-7

Adversarial barrel! an evaluation of 3d physical adversarial attacks

M Zarei, C Ward, J Harguess, M Aiken

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), 1-6

Exploring the effect of adversarial attacks on deep learning architectures for x-ray data

I Bankole-Hameed, A Parikh, J Harguess

2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), 1-9

Metrics for evaluating adversarial attack patterns

S Smith, S Muto, A Evans, CM Ward, J Harguess, E Holt

2022 SPIE DCS Geospatial Informatics XII 12099, 115-127

A Dynamic Thermal IR Display for Physical Adversarial Attacks

S Bendelac, K Manville, J Harguess, M Rodriguez

2021 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), 1-7

Physical adversarial attacks in simulated environments

M Threet, C Busho, J Harguess, M Jutras, N Lape, S Leary, K Manville, ...

2021 IEEE applied imagery pattern recognition workshop (AIPR), 1-5

Baseline evaluation methodology for adversarial patterns on object detection models

E Holt, A Malkastian, S Smith, C Ward, J Harguess

2021 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), 1-6

The vulnerability of UAVs: An adversarial machine learning perspective

M Doyle, J Harguess, K Manville, M Rodriguez

2021 SPIE DCS Geospatial Informatics XI 11733, 81-92

Adversarial attack attribution: discovering attributable signals in adversarial ML attacks

M Dotter, S Xie, K Manville, J Harguess, C Busho, M Rodriguez

AAAI 2021 Workshop: Towards Robust, Secure and Efficient Machine Learning