works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

cs.LG2026

ProxyGuard: Direct Reliability Inference for Randomized Data Release Mechanisms with Shared Targets

Dipesh Tharu Mahato, Pramod Dhungana

Researchers often choose a proxy dataset from many releases, transformations, or seeds. Search can make an invalid release appear adequate, while one adequate release does not esta…

cs.LG2026

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models

Deepanshu Mody, Samarth Agarwal, Utkarsh Mittal +1

The paper investigates how to suppress specific internal activations in large language models by optimizing only the input prompt, aiming to hide evaluation-awareness signals witho…

cs.CV2026

Early Warning Signals for OpenVLA Failure under Visual Distribution Shift

Dipesh Tharu Mahato, Rachel Ren

Visual shifts can cause a vision-language-action policy to fail after initially plausible behavior. We ask whether OpenVLA's internal activations contain signals associated with th…

cs.CY2026

Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants

Dipesh Tharu Mahato

A refusal rate neither identifies which component intervened nor measures its burden on legitimate users. This paper evaluates safeguards for dual-use biology assistants at the act…

cs.LG2025

TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift

Dipesh Tharu Mahato, Rohan Poudel, Pramod Dhungana

Deep neural networks often achieve high accuracy, but ensuring their reliability under adversarial and distributional shifts remains a pressing challenge. We propose TriGuard, a un…