Related papers: Spoofing Attacker Also Benefits from Self-Supervis…

This study investigates the explainability of embedding representations, specifically those used in modern audio spoofing detection systems based on deep neural networks, known as spoof embeddings. Building on established work in speaker…

We introduce a post-training approach that adapts self-supervised learning (SSL) models for deepfake speech detection by bridging the gap between general pre-training and domain-specific fine-tuning. We present AntiDeepfake models, a series…

Adversarial attacks have become a major threat for machine learning applications. There is a growing interest in studying these attacks in the audio domain, e.g, speech and speaker recognition; and find defenses against them. In this work,…

Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall…

Like many other tasks involving neural networks, Speech Recognition models are vulnerable to adversarial attacks. However recent research has pointed out differences between attacks and defenses on ASR models compared to image models.…

Convolutional Neural Networks and Deep Learning classification systems in general have been shown to be vulnerable to attack by specially crafted data samples that appear to belong to one class but are instead classified as another,…

Robust speaker recognition, including in the presence of malicious attacks, is becoming increasingly important and essential, especially due to the proliferation of several smart speakers and personal agents that interact with an…

Recent studies have demonstrated the vulnerability of recommender systems to data privacy attacks. However, research on the threat to model privacy in recommender systems, such as model stealing attacks, is still in its infancy. Some…

Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is,…

Self-supervised learning (SSL) speech representation models, trained on large speech corpora, have demonstrated effectiveness in extracting hierarchical speech embeddings through multiple transformer layers. However, the behavior of these…

The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. However, this openness also brings significant security risks, including…

In this paper, we extend previous self-supervised approaches for language identification by experimenting with Conformer based architecture in a multilingual pre-training paradigm. We find that pre-trained speech models optimally encode…

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature…

In this paper, a new method of training pipeline is discussed to achieve significant performance on the task of anti-spoofing with RGB image. We explore and highlight the impact of using pseudo-depth to pre-train a network that will be used…

Large language models are shown to present privacy risks through memorization of training data, and several recent works have studied such risks for the pre-training phase. Little attention, however, has been given to the fine-tuning phase…

Recently, unsupervised adversarial training (AT) has been highlighted as a means of achieving robustness in models without any label information. Previous studies in unsupervised AT have mostly focused on implementing self-supervised…

Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech, and recently emerged adversarial attacks. Great efforts have been dedicated to…

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…

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

Recent Active Learning (AL) approaches in Natural Language Processing (NLP) proposed using off-the-shelf pretrained language models (LMs). In this paper, we argue that these LMs are not adapted effectively to the downstream task during AL…