activity
20192021
most citedSSD: A Unified Framework for Self-Supervised Outlier Detection

44 citations · 93 across the 5 of their papers we have counts for

collaborators

10 papers

cs.LG2021

Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries

Arjun Nitin Bhagoji, Daniel Cullina, Vikash Sehwag +1

Understanding the fundamental limits of robust supervised learning has emerged as a problem of immense interest, from both practical and theoretical standpoints. In particular, it…

cs.CV202144 cited

SSD: A Unified Framework for Self-Supervised Outlier Detection

Vikash Sehwag, Mung Chiang, Prateek Mittal

We ask the following question: what training information is required to design an effective outlier/out-of-distribution (OOD) detector, i.e., detecting samples that lie far away fr…

cs.LG2020

RobustBench: a standardized adversarial robustness benchmark

Francesco Croce, Maksym Andriushchenko, Vikash Sehwag +5

As a research community, we are still lacking a systematic understanding of the progress on adversarial robustness which often makes it hard to identify the most promising ideas in…

cs.LG20208 cited

A Critical Evaluation of Open-World Machine Learning

Liwei Song, Vikash Sehwag, Arjun Nitin Bhagoji +1

Open-world machine learning (ML) combines closed-world models trained on in-distribution data with out-of-distribution (OOD) detectors, which aim to detect and reject OOD inputs. P…

cs.LG2020

Fast-Convergent Federated Learning

Hung T. Nguyen, Vikash Sehwag, Seyyedali Hosseinalipour +3

Federated learning has emerged recently as a promising solution for distributing machine learning tasks through modern networks of mobile devices. Recent studies have obtained lowe…

cs.CV202012 cited

Time for a Background Check! Uncovering the impact of Background Features on Deep Neural Networks

Vikash Sehwag, Rajvardhan Oak, Mung Chiang +1

With increasing expressive power, deep neural networks have significantly improved the state-of-the-art on image classification datasets, such as ImageNet. In this paper, we invest…