Related papers: Phonemic Adversarial Attack against Audio Recognit…

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time. Recent defenses have been shown to improve adversarial robustness by detecting anomalous deviations from…

Deep neural networks have been proven to be vulnerable to adversarial examples and various methods have been proposed to defend against adversarial attacks for natural language processing tasks. However, previous defense methods have…

Adversarial examples are inputs with imperceptible perturbations that easily misleading deep neural networks(DNNs). Recently, adversarial patch, with noise confined to a small and localized patch, has emerged for its easy feasibility in…

Recently demonstrated physical-world adversarial attacks have exposed vulnerabilities in perception systems that pose severe risks for safety-critical applications such as autonomous driving. These attacks place adversarial artifacts in the…

Anomalous sound detection (ASD) is one of the most significant tasks of mechanical equipment monitoring and maintaining in complex industrial systems. In practice, it is vital to precisely identify abnormal status of the working mechanical…

This paper presents an adversarial learning method for recognition-synthesis based non-parallel voice conversion. A recognizer is used to transform acoustic features into linguistic representations while a synthesizer recovers output…

Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most effective method to defend against adversarial attacks.…

Autonomous vehicles increasingly utilize the vision-based perception module to acquire information about driving environments and detect obstacles. Correct detection and classification are important to ensure safe driving decisions.…

A method for statistical parametric speech synthesis incorporating generative adversarial networks (GANs) is proposed. Although powerful deep neural networks (DNNs) techniques can be applied to artificially synthesize speech waveform, the…

In this work, we present INTACT, a novel two-phase framework designed to enhance the robustness of deep neural networks (DNNs) against noisy LiDAR data in safety-critical perception tasks. INTACT combines meta-learning with adversarial…

Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security vulnerabilities. We propose a universal targeted latent space attack, an encoder-level adversarial…

Adversarial patch-based attacks aim to fool a neural network with an intentionally generated noise, which is concentrated in a particular region of an input image. In this work, we perform an in-depth analysis of different patch generation…

Audio adversarial examples (AEs) have posed significant security challenges to real-world speaker recognition systems. Most black-box attacks still require certain information from the speaker recognition model to be effective (e.g.,…

Voice anonymization systems aim to protect speaker privacy by obscuring vocal traits while preserving the linguistic content relevant for downstream applications. However, because these linguistic cues remain intact, they can be exploited…

The success of adversarial attacks to speaker recognition is mainly in white-box scenarios. When applying the adversarial voices that are generated by attacking white-box surrogate models to black-box victim models, i.e.…

Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems. Especially, deep neural network (DNN) methods have significantly reduced estimation errors for crowd counting missions. Recent studies…

Attacking deep learning based biometric systems has drawn more and more attention with the wide deployment of fingerprint/face/speaker recognition systems, given the fact that the neural networks are vulnerable to the adversarial examples,…

Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural…

Recent advances in text-to-speech technologies have enabled realistic voice generation, fueling audio-based deepfake attacks such as fraud and impersonation. While audio anti-spoofing systems are critical for detecting such threats, prior…

Many applications of speech technology require more and more audio data. Automatic assessment of the quality of the collected recordings is important to ensure they meet the requirements of the related applications. However, effective and…