Adversarial Robustness and Explainability of Machine Learning Models

Jamil Gafur; Steve Goddard; William Lai

doi:10.1145/3626203.3670522

Back

Adversarial Robustness and Explainability of Machine Learning Models

Conference proceeding

Open access

Adversarial Robustness and Explainability of Machine Learning Models

Jamil Gafur, Steve Goddard and William Lai

Practice and Experience in Advanced Research Computing 2024: Human Powered Computing, pp.1-7

ACM Conferences

PEARC '24: Practice and Experience in Advanced Research Computing

07/17/2024

DOI: 10.1145/3626203.3670522

Appears in UI Libraries Support Open Access

Files and links (1)

url

https://doi.org/10.1145/3626203.3670522View

Published (Version of record) Open Access

Abstract

The rapid advancement of machine learning has brought forth sophisticated neural network models harnessing computational prowess and vast datasets for diverse applications. Nonetheless, with the proliferation of these complex models, apprehensions have surfaced regarding their resilience, interpretability, and biases. To mitigate these concerns, we propose the “Adversarial Observation” framework, amalgamating explainable and adversarial methodologies for comprehensive neural network scrutiny. By integrating explainable techniques, users gain profound insights into the model’s internal mechanisms, fostering transparency and facilitating bias identification. This framework aims to enhance the trustworthiness and accountability of neural network systems amidst their expanding utility.

Computer systems organization -- Embedded and cyber-physical systems -- Embedded systems

Computing methodologies -- Artificial intelligence -- Natural language processing

Computing methodologies -- Artificial intelligence -- Natural language processing -- Information extraction

UIOWA OA Agreement

Details

Title: Subtitle: Adversarial Robustness and Explainability of Machine Learning Models
Creators: Jamil Gafur - University of Iowa
Steve Goddard - University of Iowa
William Lai - Cornell University
Contributors: Shawn T. Brown (Editor) - Hewlett Packard Enterprise (United States)
Barr Von Oehsen (Editor) - Pittsburgh Supercomputing Center
Eric Adams (Editor) - Purdue University West Lafayette
Eva Siegmann (Editor) - Stony Brook University
Resource Type: Conference proceeding
Publication Details: Practice and Experience in Advanced Research Computing 2024: Human Powered Computing, pp.1-7
Conference: PEARC '24: Practice and Experience in Advanced Research Computing
Series: ACM Conferences
DOI: 10.1145/3626203.3670522
Publisher: Association for Computing Machinery (ACM)
Language: English
Date published: 07/17/2024
Academic Unit: Computer Science
Record Identifier: 9984658256002771

Metrics

29 Record Views

1 Times Cited - Web of Science