Related papers: Interpretable Spectrum Transformation Attacks to S…
Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "transfer" to attack other learning models. In this paper, we…
With the development of deep learning, speech enhancement has been greatly optimized in terms of speech quality. Previous methods typically focus on the discriminative supervised learning or generative modeling, which tends to introduce…
We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50 characters per…
Data efficient voice cloning aims at synthesizing target speaker's voice with only a few enrollment samples at hand. To this end, speaker adaptation and speaker encoding are two typical methods based on base model trained from multiple…
Thanks to the latest deep learning algorithms, silent speech interfaces (SSI) are now able to synthesize intelligible speech from articulatory movement data under certain conditions. However, the resulting models are rather…
This paper shows the susceptibility of spectrogram-based audio classifiers to adversarial attacks and the transferability of such attacks to audio waveforms. Some commonly used adversarial attacks to images have been applied to…
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…
Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. This paper proposes a hierarchical network with transformer encoders and memory mechanism to address this problem. The proposed…
There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR…
The increasing prevalence of microphones in everyday devices and the growing reliance on online services have amplified the risk of acoustic side-channel attacks (ASCAs) targeting keyboards. This study explores deep learning techniques,…
In recent years, deep learning (DL) models have achieved significant progress in many domains, such as autonomous driving, facial recognition, and speech recognition. However, the vulnerability of deep learning models to adversarial attacks…
Speech emotion recognition plays an important role in building more intelligent and human-like agents. Due to the difficulty of collecting speech emotional data, an increasingly popular solution is leveraging a related and rich source…
Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates the need for direct access to the victim model during an…
Synthetic speech detection is one of the most important research problems in audio security. Meanwhile, deep neural networks are vulnerable to adversarial attacks. Therefore, we establish a comprehensive benchmark to evaluate the…
Transferable Targeted Attacks (TTAs) face significant challenges due to severe overfitting to surrogate models. Recent breakthroughs heavily rely on large-scale training data of victim models, while data-free solutions, \textit{i.e.}, image…
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…
Adversarial attacks introduce small, deliberately crafted perturbations that mislead neural networks, and their transferability from white-box to black-box target models remains a critical research focus. Input transformation-based attacks…
Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately…
In end-to-end speech translation, acoustic representations learned by the encoder are usually fixed and static, from the perspective of the decoder, which is not desirable for dealing with the cross-modal and cross-lingual challenge in…
Modern image-to-text systems typically adopt the encoder-decoder framework, which comprises two main components: an image encoder, responsible for extracting image features, and a transformer-based decoder, used for generating captions.…