相关论文: SoundBreak: A Systematic Study of Audio-Only Adver…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced the naturalness and flexibility of human computer interaction by enabling seamless understanding across text, vision, and audio modalities. Among these,…

Large Audio-language Models (LAMs) have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models (LLMs). However, the security of LAMs under adversarial attacks remains underexplored,…

Despite the excellent performance of neural-network-based audio source separation methods and their wide range of applications, their robustness against intentional attacks has been largely neglected. In this work, we reformulate various…

Self-supervised language and audio models effectively predict brain responses to speech. However, traditional prediction models rely on linear mappings from unimodal features, despite the complex integration of auditory signals with…

Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction…

Conditional sound separation in multi-source audio mixtures without having access to single source sound data during training is a long standing challenge. Existing mix-and-separate based methods suffer from significant performance drop…

Training on multiple modalities of input can augment the capabilities of a language model. Here, we ask whether such a training regime can improve the quality and efficiency of these systems as well. We focus on text--audio and introduce…

The emergence of large-scale automatic speech recognition (ASR) models such as Whisper has greatly expanded their adoption across diverse real-world applications. Ensuring robustness against even minor input perturbations is therefore…

Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start from audio alone and actively search for cross-modal evidence remains underexplored. In…

Recent developments in large speech foundation models like Whisper have led to their widespread use in many automatic speech recognition (ASR) applications. These systems incorporate `special tokens' in their vocabulary, such as…

Contextual question-answering models are susceptible to adversarial perturbations to input context, commonly observed in real-world scenarios. These adversarial noises are designed to degrade the performance of the model by distorting the…

In a transfer-based attack against Automatic Speech Recognition (ASR) systems, attacks are unable to access the architecture and parameters of the target model. Existing attack methods are mostly investigated in voice assistant scenarios…

Multimodal learning is defined as learning over multiple heterogeneous input modalities such as video, audio, and text. In this work, we are concerned with understanding how models behave as the type of modalities differ between training…

With the widespread application of automatic speech recognition (ASR) systems, their vulnerability to adversarial attacks has been extensively studied. However, most existing adversarial examples are generated on specific individual models,…

Recent advancements in adversarial attacks have demonstrated their effectiveness in misleading speaker recognition models, making wrong predictions about speaker identities. On the other hand, defense techniques against speaker-adversarial…

Audio-visual active speaker detection (AVASD) is well-developed, and now is an indispensable front-end for several multi-modal applications. However, to the best of our knowledge, the adversarial robustness of AVASD models hasn't been…

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…

As audio/visual classification models are widely deployed for sensitive tasks like content filtering at scale, it is critical to understand their robustness along with improving the accuracy. This work aims to study several key questions…

As audio-visual systems are being deployed for safety-critical tasks such as surveillance and malicious content filtering, their robustness remains an under-studied area. Existing published work on robustness either does not scale to…

Audio processing models based on deep neural networks are susceptible to adversarial attacks even when the adversarial audio waveform is 99.9% similar to a benign sample. Given the wide application of DNN-based audio recognition systems,…