5 papers · 1 filter
Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs
Rao Ma, Mengjie Qian, Vyas Raina +2
The combination of pre-trained speech encoders with large language models has enabled the development of speech LLMs that can handle a wide range of spoken language processing task…
Extreme Miscalibration and the Illusion of Adversarial Robustness
Vyas Raina, Samson Tan, Volkan Cevher +3
Deep learning-based Natural Language Processing (NLP) models are vulnerable to adversarial attacks, where small perturbations can cause a model to misclassify. Adversarial Training…
LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History
Akash Gupta, Ivaxi Sheth, Vyas Raina +2
With the recent emergence of powerful instruction-tuned large language models (LLMs), various helpful conversational Artificial Intelligence (AI) systems have been deployed across…
Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models
Vyas Raina, Rao Ma, Charles McGhee +2
Recent developments in large speech foundation models like Whisper have led to their widespread use in many automatic speech recognition (ASR) applications. These systems incorpora…
Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment
Vyas Raina, Adian Liusie, Mark Gales
Large Language Models (LLMs) are powerful zero-shot assessors used in real-world situations such as assessing written exams and benchmarking systems. Despite these critical applica…