Bhiksha Raj

Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy

2021 · arXiv (Cornell University)

This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood around each training example, such that the label …

SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning

2023 · arXiv (Cornell University)

The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling …

Privacy-oriented manipulation of speaker representations

2023 · arXiv (Cornell University)

Speaker embeddings are ubiquitous, with applications ranging from speaker recognition and diarization to speech synthesis and voice anonymisation. The amount of information held by these embeddings lends them versatility, but also raises privacy concerns. Speaker …