相关论文: Introducing Model Inversion Attacks on Automatic S…

Recently, diffusion models have become popular tools for image synthesis because of their high-quality outputs. However, like other large-scale models, they may leak private information about their training data. Here, we demonstrate a…

Label smoothing -- using softened labels instead of hard ones -- is a widely adopted regularization method for deep learning, showing diverse benefits such as enhanced generalization and calibration. Its implications for preserving model…

Spoofing attacks posed by generating artificial speech can severely degrade the performance of a speaker verification system. Recently, many anti-spoofing countermeasures have been proposed for detecting varying types of attacks from…

Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target speakers as clues,…

Domain generalization remains a critical problem for speaker recognition, even with the state-of-the-art architectures based on deep neural nets. For example, a model trained on reading speech may largely fail when applied to scenarios of…

Despite the broad application of Machine Learning models as a Service (MLaaS), they are vulnerable to model stealing attacks. These attacks can replicate the model functionality by using the black-box query process without any prior…

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 speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight…

Deep speech classification has achieved tremendous success and greatly promoted the emergence of many real-world applications. However, backdoor attacks present a new security threat to it, particularly with untrustworthy third-party…

This paper proposes a guided speaker embedding extraction system, which extracts speaker embeddings of the target speaker using speech activities of target and interference speakers as clues. Several methods for long-form overlapped…

It is observed in the literature that data augmentation can significantly mitigate membership inference (MI) attack. However, in this work, we challenge this observation by proposing new MI attacks to utilize the information of augmented…

Membership inference attacks allow a malicious entity to predict whether a sample is used during training of a victim model or not. State-of-the-art membership inference attacks have shown to achieve good accuracy which poses a great…

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

Data augmentation has proven to be a promising prospect in improving the performance of deep learning models by adding variability to training data. In previous work with developing a noise robust acoustic-to-articulatory speech inversion…

Membership Inference attacks (MIAs) aim to predict whether a data sample was present in the training data of a machine learning model or not, and are widely used for assessing the privacy risks of language models. Most existing attacks rely…

Large-scale pretrained models using self-supervised learning have reportedly improved the performance of speech anti-spoofing. However, the attacker side may also make use of such models. Also, since it is very expensive to train such…

Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training data. To defend against MI attacks, previous work utilizes a…

End-to-end models are fast replacing the conventional hybrid models in automatic speech recognition. Transformer, a sequence-to-sequence model, based on self-attention popularly used in machine translation tasks, has given promising results…

Language model inversion seeks to recover hidden prompts using only language model outputs. This capability has implications for security and accountability in language model deployments, such as leaking private information from an…

Federated learning is known for its capability to safeguard the participants' data privacy. However, recently emerged model inversion attacks (MIAs) have shown that a malicious parameter server can reconstruct individual users' local data…