Bhavya Kailkhura

17

Papers

7

Total Citations

Papers (17)

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention

Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Position: TrustLLM: Trustworthiness in Large Language Models

How Robust Are Randomized Smoothing Based Defenses to Data Poisoning?

Scalability vs. Utility: Do We Have To Sacrifice One for the Other in Data Importance Quantification?

On the Design of Black-Box Adversarial Examples by Leveraging Gradient-Free Optimization and Operator Splitting Method

Can Shape Structure Features Improve Model Robustness Under Diverse Adversarial Settings?

A Spectral View of Randomized Smoothing under Common Corruptions: Benchmarking and Improving Certified Robustness

Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning

A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness

G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning

Models Out of Line: A Fourier Lens on Distribution Shift Robustness

Neural Image Compression: Generalization, Robustness, and Spectral Biases