Related papers: IO-RAE: Information-Obfuscation Reversible Adversa…
Image AutoRegressive generation has emerged as a new powerful paradigm with image autoregressive models (IARs) matching state-of-the-art diffusion models (DMs) in image quality (FID: 1.48 vs. 1.58) while allowing for a higher generation…
Reverberation, which is generally caused by sound reflections from walls, ceilings, and floors, can result in severe performance degradation of acoustic applications. Due to a complicated combination of attenuation and time-delay effects,…
Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to…
Evasion attacks pose significant threats to AI systems, exploiting vulnerabilities in machine learning models to bypass detection mechanisms. The widespread use of voice data, including deepfakes, in promising future industries is currently…
In this paper, we propose a cooperative approach to improve the security of both primary and secondary systems in cognitive radio multicast communications. During their access to the frequency spectrum licensed to the primary users, the…
A targeted adversarial attack produces audio samples that can force an Automatic Speech Recognition (ASR) system to output attacker-chosen text. To exploit ASR models in real-world, black-box settings, an adversary can leverage the…
Music adversarial attacks have garnered significant interest in the field of Music Information Retrieval (MIR). In this paper, we present Music Adversarial Inpainting Attack (MAIA), a novel adversarial attack framework that supports both…
Audio deepfakes pose significant threats, including impersonation, fraud, and reputation damage. To address these risks, audio deepfake detection (ADD) techniques have been developed, demonstrating success on benchmarks like ASVspoof2019.…
Deep Reinforcement Learning (DRL) policies are highly susceptible to adversarial noise in observations, which poses significant risks in safety-critical scenarios. The challenge inherent to adversarial perturbations is that by altering the…
Speech data conveys sensitive speaker attributes like identity or accent. With a small amount of found data, such attributes can be inferred and exploited for malicious purposes: voice cloning, spoofing, etc. Anonymization aims to make the…
Speaker recognition is a popular topic in biometric authentication and many deep learning approaches have achieved extraordinary performances. However, it has been shown in both image and speech applications that deep neural networks are…
We present AERO, a audio super-resolution model that processes speech and music signals in the spectral domain. AERO is based on an encoder-decoder architecture with U-Net like skip connections. We optimize the model using both time and…
Speech embeddings often retain sensitive attributes such as speaker identity, accent, or demographic information, posing risks in biased model training and privacy leakage. We propose WavShape, an information-theoretic speech representation…
Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…
Neural models enjoy widespread use across a variety of tasks and have grown to become crucial components of many industrial systems. Despite their effectiveness and extensive popularity, they are not without their exploitable flaws.…
Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of…
By adding users as a new dimension to connectivity, on-body Internet-of-Things (IoT) devices have gained considerable momentum in recent years, while raising serious privacy and safety issues. Existing approaches to authenticate these…
The preservation of privacy has emerged as a critical topic in the era of artificial intelligence. However, current work focuses on user-oriented privacy, overlooking severe enterprise data leakage risks exacerbated by the…
Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural Networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent…
Recent advances in machine learning techniques are enabling Automated Speech Recognition (ASR) more accurate and practical. The evidence of this can be seen in the rising number of smart devices with voice processing capabilities. More and…