Under copyright Constraint(s) on Use: This work is protected by the U.S. Copyright Law (Title 17, U.S.C.). Use of this work beyond that allowed by "fair use" or any license applied to this work requires written permission of the copyright holder(s). Responsibility for obtaining permissions and any use and distribution of this work rests exclusively with the user and not the UC San Diego Library. Inquiries can be made to the UC San Diego Library program having custody of the work. Use: This work is available from the UC San Diego Library. This digital copy of the work is intended to support research, teaching, and private study.
As machine learning (ML) has gained prominence in the business world, the implementation of deep neural networks (DNN) has become more widespread. The security of DNN models has recently come under scrutiny as they are at risk of adversarial attacks such as backdoor Trojan attacks. These attacks depend on a trigger to activate malicious behavior. Due to the lack of transparency in DNNs, the effects of Trojans may remain undetected until activated by an attacker. This project demonstrates a significant reduction in the time and resources necessary to detect a poisoned model through the use of dimensionality reduction techniques. The detector utilizes Principal Component Analysis and Independent Component Analysis to reduce model weights that can then be used to train a classification model. This work builds on previous research, integrating reduction techniques to significantly reduce inference time while maintaining model accuracy at 85%. Are you protected from malicious AI? Jacobs School of Engineering Data Science and Engineering Masters of Applied Science Program (DSE MAS) DSE 260 Capstone Project. Research Data Curation Program, UC San Diego, La Jolla, 92093-0175 (https://lib.ucsd.edu/rdcp) This project relies on external software packages, modules/libraries, or programs, use of which may carry specific license requirements. Users should comply with any licenses specified within the contents of this project. Armstrong, Christopher; Hartley, Daniel; Hutton, Spencer; Quach, Shirley (2023). Trojan Attack Prediction. In Data Science & Engineering Master of Advanced Study (DSE MAS) Capstone Projects. UC San Diego Library Digital Collections. https://doi.org/10.6075/J0B56JX8
Type
dataset
Identifier
ark:/20775/bb6529767h
Language
English
Subject
Deep learning Task: Image classification Task: Classification Trojan classification Neural network Trojan attack prediction Security Data Science & Engineering Master of Advanced Study (DSE MAS) Cyber security Capstone projects Machine learning Convolutional Neural Network (CNN) National Institute of Standards and Technology (NIST) DSE MAS - 2023 Cohort
If you're wondering about permissions and what you can do with this item, a good starting point is the "rights information" on this page. See our terms of use for more tips.
Share your story
Has Calisphere helped you advance your research, complete a project, or find something meaningful? We'd love to hear about it; please send us a message.
