Related papers: Learning to fool the speaker recognition

This work presents a novel framework based on feed-forward neural network for text-independent speaker classification and verification, two related systems of speaker recognition. With optimized features and model training, it achieves 100%…

The rapid advancement of generative AI has made audio deepfakes increasingly indistinguishable from authentic human vocals, posing significant threats to persons-of-interest (POI) such as public figures. Current detection systems primarily…

In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approaches, our method targets up to 50 speakers simultaneously,…

Recent years have seen a surge in the popularity of acoustics-enabled personal devices powered by machine learning. Yet, machine learning has proven to be vulnerable to adversarial examples. A large number of modern systems protect…

In the rapidly evolving landscape of digital security, biometric authentication systems, particularly facial recognition, have emerged as integral components of various security protocols. However, the reliability of these systems is…

Facial recognition system is one of the major successes of Artificial intelligence and has been used a lot over the last years. But, images are not the only biometric present: audio is another possible biometric that can be used as an…

Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and…

Automatic speaker verification (ASV) technology is recently finding its way to end-user applications for secure access to personal data, smart services or physical facilities. Similar to other biometric technologies, speaker verification is…

A number of studies have successfully developed speaker verification or presentation attack detection systems. However, studies integrating the two tasks remain in the preliminary stages. In this paper, we propose two approaches for…

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where the adversaries can…

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…

Current state-of-the-art speech recognition models are trained to map acoustic signals into sub-lexical units. While these models demonstrate superior performance, they remain vulnerable to out-of-distribution conditions such as background…

Speaker Recognition is a challenging task with essential applications such as authentication, automation, and security. The SincNet is a new deep learning based model which has produced promising results to tackle the mentioned task. To…

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We…

Speech recognition in cocktail-party environments remains a significant challenge for state-of-the-art speech recognition systems, as it is extremely difficult to extract an acoustic signal of an individual speaker from a background of…

In this study, we propose a timbre-reserved adversarial attack approach for speaker identification (SID) to not only exploit the weakness of the SID model but also preserve the timbre of the target speaker in a black-box attack setting.…

Membership inference attacks allow adversaries to determine whether a particular example was contained in the model's training dataset. While previous works have confirmed the feasibility of such attacks in various applications, none has…

Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural Networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent…

Wav2vec2 has achieved success in applying Transformer architecture and self-supervised learning to speech recognition. Recently, these have come to be used not only for speech recognition but also for the entire speech processing. This…

Speaker verification systems are vulnerable to spoofing attacks which presents a major problem in their real-life deployment. To date, most of the proposed synthetic speech detectors (SSDs) have weighted the importance of different segments…