Arun Balaji Buduru

BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization

2024 · arXiv (Cornell University)

Deep Learning has become popular due to its vast applications in almost all domains. However, models trained using deep learning are prone to failure for adversarial samples and carry a considerable risk in sensitive applications. …

Towards Machine Unlearning for Paralinguistic Speech Processing

2025 · arXiv (Cornell University)

In this work, we pioneer the study of Machine Unlearning (MU) for Paralinguistic Speech Processing (PSP). We focus on two key PSP tasks: Speech Emotion Recognition (SER) and Depression Detection (DD). To this end, we …