Related papers: Generative Extraction of Audio Classifiers for Spe…
Computational paralinguistic analysis is increasingly being used in a wide range of cyber applications, including security-sensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While…
Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal data. Speaker anonymization aims to remove speaker information…
Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…
The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repeating words from…
In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…
Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. This transition, however, introduces a distinct class of…
With the advancement of audio generation, generative models can produce highly realistic audios. However, the proliferation of deepfake general audio can pose negative consequences. Therefore, we propose a new task, deepfake general audio…
Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that…
The advancements in audio generative models have opened up new challenges in their responsible disclosure and the detection of their misuse. In response, we introduce a method to watermark latent generative models by a specific watermarking…
Memorization presents a challenge for several constrained Natural Language Generation (NLG) tasks such as Neural Machine Translation (NMT), wherein the proclivity of neural models to memorize noisy and atypical samples reacts adversely with…
Despite significant advances in deep models for music generation, the use of these techniques remains restricted to expert users. Before being democratized among musicians, generative models must first provide expressive control over the…
Autoregressive models based on Transformers have become the prevailing approach for generating music compositions that exhibit comprehensive musical structure. These models are typically trained by minimizing the negative log-likelihood…
The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to…
Automatic speaker verification systems are increasingly used as the primary means to authenticate costumers. Recently, it has been proposed to train speaker verification systems using end-to-end deep neural models. In this paper, we show…
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…
Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate…
Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this paper, we propose a novel generation-network-based approach, called…
Deep neural networks are vulnerable to adversarial examples that mislead models with imperceptible perturbations. In audio, although adversarial examples have achieved incredible attack success rates on white-box settings and black-box…
We propose to implement speech enhancement by the regeneration of clean speech from a salient representation extracted from the noisy signal. The network that extracts salient features is trained using a set of weight-sharing clones of the…
Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model's structure, parameters, or training data. The adversary can only access the target model's…