Constructing Robust Classifiers Using Cryptographic Objects.

Date of Submission

December 2020

Date of Award

Winter 12-12-2021

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science

Department

Cryptology and Security Research Unit (CSRU-Kolkata)

Supervisor

Chakraborty, Debrup (CSRU-Kolkata; ISI)

Abstract (Summary of the Work)

The existence of evasion attacks during the test phase of machine learning algorithms represents a significant challenge to their deployment and understanding. These attacks are carried out by adding imperceptible perturbations to the inputs to generate adversarial examples. As of now designing good robust classifiers in real life seems very difficult. But so far most of the studies depict the relationship between computational power of adversary and robustness of the classifier. In this report, we have used some of the cryptographic schemes to create robust classifiers and show the dependency of robustness with adversarial budget.

Comments

ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28842689

Control Number

ISI-DISS-2020-08

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

DOI

http://dspace.isical.ac.in:8080/jspui/handle/10263/7159

This document is currently not available here.

Share

COinS