Picture for Kavita Kumari

Kavita Kumari

University of Texas, San Antonio

Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks

Add code
Apr 10, 2024
Figure 1 for Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks
Figure 2 for Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks
Figure 3 for Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks
Figure 4 for Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks
Viaarxiv icon

DeepEclipse: How to Break White-Box DNN-Watermarking Schemes

Add code
Mar 06, 2024
Viaarxiv icon

DEMASQ: Unmasking the ChatGPT Wordsmith

Add code
Nov 08, 2023
Figure 1 for DEMASQ: Unmasking the ChatGPT Wordsmith
Figure 2 for DEMASQ: Unmasking the ChatGPT Wordsmith
Figure 3 for DEMASQ: Unmasking the ChatGPT Wordsmith
Figure 4 for DEMASQ: Unmasking the ChatGPT Wordsmith
Viaarxiv icon

To ChatGPT, or not to ChatGPT: That is the question!

Add code
Apr 05, 2023
Viaarxiv icon

BayBFed: Bayesian Backdoor Defense for Federated Learning

Add code
Jan 23, 2023
Viaarxiv icon

A Game-theoretic Understanding of Repeated Explanations in ML Models

Add code
Feb 05, 2022
Figure 1 for A Game-theoretic Understanding of Repeated Explanations in ML Models
Figure 2 for A Game-theoretic Understanding of Repeated Explanations in ML Models
Figure 3 for A Game-theoretic Understanding of Repeated Explanations in ML Models
Figure 4 for A Game-theoretic Understanding of Repeated Explanations in ML Models
Viaarxiv icon