Related papers: Generative Extraction of Audio Classifiers for Spe…

We propose listen to extract (LExt), a highly-effective while extremely-simple algorithm for monaural target speaker extraction (TSE). Given an enrollment utterance of a target speaker, LExt aims at extracting the target speaker from the…

Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property (IP) of machine-learning-as-a-service (MLaaS) providers. Defending against such attacks is…

Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms…

Information leakage is becoming a critical problem as various information becomes publicly available by mistake, and machine learning models train on that data to provide services. As a result, one's private information could easily be…

This paper is about developing personalized speech synthesis systems with recordings of mildly impaired speech. In particular, we consider consonant and vowel alterations resulted from partial glossectomy, the surgical removal of part of…

Model Extraction attacks exploit the target model's prediction API to create a surrogate model in order to steal or reconnoiter the functionality of the target model in the black-box setting. Several recent studies have shown that a…

In model extraction attacks, adversaries can steal a machine learning model exposed via a public API by repeatedly querying it and adjusting their own model based on obtained predictions. To prevent model stealing, existing defenses focus…

Current graph neural network (GNN) model-stealing methods rely heavily on queries to the victim model, assuming no hard query limits. However, in reality, the number of allowed queries can be severely limited. In this paper, we demonstrate…

Generative sequence models are typically trained on sample sequences from natural or formal languages. It is a crucial question whether -- or to what extent -- sample-based training is able to capture the true structure of these languages,…

Model-based attacks can infer training data information from deep neural network models. These attacks heavily depend on the attacker's knowledge of the application domain, e.g., using it to determine the auxiliary data for model-inversion…

Speech super-resolution (SR) is the task that restores high-resolution speech from low-resolution input. Existing models employ simulated data and constrained experimental settings, which limit generalization to real-world SR. Predictive…

Replay attack is one of the most effective and simplest voice spoofing attacks. Detecting replay attacks is challenging, according to the Automatic Speaker Verification Spoofing and Countermeasures Challenge 2021 (ASVspoof 2021), because…

Target speaker extraction is to extract the target speaker, specified by enrollment utterance, in an environment with other competing speakers. Therefore, the task needs to solve two problems, speaker identification and separation, at the…

As speech generation technology advances, the risk of misuse through deepfake audio has become a pressing concern, which underscores the critical need for robust detection systems. However, many existing speech deepfake datasets are limited…

Audio CAPTCHAs are supposed to provide a strong defense for online resources; however, advances in speech-to-text mechanisms have rendered these defenses ineffective. Audio CAPTCHAs cannot simply be abandoned, as they are specifically named…

Adversarial attacks pose a threat to deep learning models. However, research on adversarial detection methods, especially in the multi-modal domain, is very limited. In this work, we propose an efficient and straightforward detection method…

We present a novel, language-agnostic approach to "priming" language models for the task of event extraction, providing particularly effective performance in low-resource and zero-shot cross-lingual settings. With priming, we augment the…

This paper investigates a class of attacks targeting the confidentiality aspect of security in Deep Reinforcement Learning (DRL) policies. Recent research have established the vulnerability of supervised machine learning models (e.g.,…

This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. The model is fully probabilistic and autoregressive, with the predictive distribution for each audio sample conditioned on all previous ones;…

The prevailing noise-resistant and reverberation-resistant localization algorithms primarily emphasize separating and providing directional output for each speaker in multi-speaker scenarios, without association with the identity of…