most citedGradient-Based Adversarial and Out-of-Distribution Detection

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

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2023★ 7 cited

Probing the Purview of Neural Networks via Gradient Analysis

Jinsol Lee, Charlie Lehman, Mohit Prabhushankar +1

We analyze the data-dependent capacity of neural networks and assess anomalies in inputs from the perspective of networks during inference. The notion of data-dependent capacity al…

cs.LG2022★ 2 cited

Gradient-Based Adversarial and Out-of-Distribution Detection

Jinsol Lee, Mohit Prabhushankar, Ghassan AlRegib

We propose to utilize gradients for detecting adversarial and out-of-distribution samples. We introduce confounding labels -- labels that differ from normal labels seen during trai…