2 citations · 3 across the 6 of their papers we have counts for
6 papers
Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuning
Mustafa Safa Ozdayi, Charith Peris, Jack FitzGerald +5
Large Language Models (LLMs) are known to memorize significant portions of their training data. Parts of this memorized content have been shown to be extractable by simply querying…
Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Framework
Rahil Parikh, Harshavardhan Sundar, Ming Sun +2
Acoustic events are sounds with well-defined spectro-temporal characteristics which can be associated with the physical objects generating them. Acoustic scenes are collections of…
An Empirical Analysis on the Vulnerabilities of End-to-End Speech Segregation Models
Rahil Parikh, Gaspar Rochette, Carol Espy-Wilson +1
End-to-end learning models have demonstrated a remarkable capability in performing speech segregation. Despite their wide-scope of real-world applications, little is known about th…
Canary Extraction in Natural Language Understanding Models
Rahil Parikh, Christophe Dupuy, Rahul Gupta
Natural Language Understanding (NLU) models can be trained on sensitive information such as phone numbers, zip-codes etc. Recent literature has focused on Model Inversion Attacks (…
Harmonicity Plays a Critical Role in DNN Based Versus in Biologically-Inspired Monaural Speech Segregation Systems
Rahil Parikh, Ilya Kavalerov, Carol Espy-Wilson +1
Recent advancements in deep learning have led to drastic improvements in speech segregation models. Despite their success and growing applicability, few efforts have been made to a…
Acoustic To Articulatory Speech Inversion Using Multi-Resolution Spectro-Temporal Representations Of Speech Signals
Rahil Parikh, Nadee Seneviratne, Ganesh Sivaraman +2
Multi-resolution spectro-temporal features of a speech signal represent how the brain perceives sounds by tuning cortical cells to different spectral and temporal modulations. Thes…