Related papers: Multi-Discriminator Sobolev Defense-GAN Against Ad…
Separating two sources from an audio mixture is an important task with many applications. It is a challenging problem since only one signal channel is available for analysis. In this paper, we propose a novel framework for singing voice…
Adversarial attacks pose a threat to deep learning models. However, research on adversarial detection methods, especially in the multi-modal domain, is very limited. In this work, we propose an efficient and straightforward detection method…
Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…
Deep Neural Networks (DNNs) are well-known to be vulnerable to Adversarial Examples (AEs). A large amount of efforts have been spent to launch and heat the arms race between the attackers and defenders. Recently, advanced gradient-based…
A method for statistical parametric speech synthesis incorporating generative adversarial networks (GANs) is proposed. Although powerful deep neural networks (DNNs) techniques can be applied to artificially synthesize speech waveform, the…
As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…
The paper presents a novel approach of spoofing wireless signals by using a general adversarial network (GAN) to generate and transmit synthetic signals that cannot be reliably distinguished from intended signals. It is of paramount…
Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and…
The vulnerability of machine learning systems to adversarial attacks questions their usage in many applications. In this paper, we propose a randomized diversification as a defense strategy. We introduce a multi-channel architecture in a…
This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two…
In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at…
An adversarial attack is an exploitative process in which minute alterations are made to natural inputs, causing the inputs to be misclassified by neural models. In the field of speech recognition, this has become an issue of increasing…
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…
Deep generative models have achieved significant progress in speech synthesis to date, while high-fidelity singing voice synthesis is still an open problem for its long continuous pronunciation, rich high-frequency parts, and strong…
We describe an end-to-end speech synthesis system that uses generative adversarial training. We train our Vocoder for raw phoneme-to-audio conversion, using explicit phonetic, pitch and duration modeling. We experiment with several…
In the area of natural language processing, deep learning models are recently known to be vulnerable to various types of adversarial perturbations, but relatively few works are done on the defense side. Especially, there exists few…
We investigate the use of generative adversarial networks (GANs) in speech dereverberation for robust speech recognition. GANs have been recently studied for speech enhancement to remove additive noises, but there still lacks of a work to…
This paper presents a novel yet efficient defense framework for segmentation models against adversarial attacks in medical imaging. In contrary to the defense methods against adversarial attacks for classification models which widely are…
Automating arrhythmia detection from ECG requires a robust and trusted system that retains high accuracy under electrical disturbances. Many machine learning approaches have reached human-level performance in classifying arrhythmia from…
The intelligibility of natural speech is seriously degraded when exposed to adverse noisy environments. In this work, we propose a deep learning-based speech modification method to compensate for the intelligibility loss, with the…