Picture for Akshay Mehra

Akshay Mehra

Dynamic Domains, Dynamic Solutions: DPCore for Continual Test-Time Adaptation

Add code
Jun 15, 2024
Viaarxiv icon

Test-time Assessment of a Model's Performance on Unseen Domains via Optimal Transport

Add code
May 02, 2024
Viaarxiv icon

On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization

Add code
Jul 17, 2023
Viaarxiv icon

Analysis of Task Transferability in Large Pre-trained Classifiers

Add code
Jul 03, 2023
Viaarxiv icon

Understanding the Robustness of Multi-Exit Models under Common Corruptions

Add code
Dec 03, 2022
Viaarxiv icon

On Certifying and Improving Generalization to Unseen Domains

Add code
Jun 24, 2022
Figure 1 for On Certifying and Improving Generalization to Unseen Domains
Figure 2 for On Certifying and Improving Generalization to Unseen Domains
Figure 3 for On Certifying and Improving Generalization to Unseen Domains
Figure 4 for On Certifying and Improving Generalization to Unseen Domains
Viaarxiv icon

Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines

Add code
Dec 01, 2021
Figure 1 for Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
Figure 2 for Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
Figure 3 for Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
Figure 4 for Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
Viaarxiv icon

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning

Add code
Jul 08, 2021
Figure 1 for Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
Figure 2 for Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
Figure 3 for Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
Figure 4 for Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
Viaarxiv icon

Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks

Add code
Jun 15, 2021
Figure 1 for Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks
Figure 2 for Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks
Figure 3 for Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks
Figure 4 for Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks
Viaarxiv icon

How Robust are Randomized Smoothing based Defenses to Data Poisoning?

Add code
Dec 02, 2020
Figure 1 for How Robust are Randomized Smoothing based Defenses to Data Poisoning?
Figure 2 for How Robust are Randomized Smoothing based Defenses to Data Poisoning?
Figure 3 for How Robust are Randomized Smoothing based Defenses to Data Poisoning?
Figure 4 for How Robust are Randomized Smoothing based Defenses to Data Poisoning?
Viaarxiv icon