most citedExplaining Adversarial Vulnerability with a Data Sparsity Hypothesis

1 citations · 1 across the 2 of their papers we have counts for

collaborators

2 papers

cs.LG2022

PaRT: Parallel Learning Towards Robust and Transparent AI

Mahsa Paknezhad, Hamsawardhini Rengarajan, Chenghao Yuan +4

This paper takes a parallel learning approach for robust and transparent AI. A deep neural network is trained in parallel on multiple tasks, where each task is trained only on a su…

cs.AI2021★ 1 cited

Explaining Adversarial Vulnerability with a Data Sparsity Hypothesis

Mahsa Paknezhad, Cuong Phuc Ngo, Amadeus Aristo Winarto +4

Despite many proposed algorithms to provide robustness to deep learning (DL) models, DL models remain susceptible to adversarial attacks. We hypothesize that the adversarial vulner…