相关论文: Fooling End-to-end Speaker Verification by Adversa…

Recent years have seen a surge in the popularity of acoustics-enabled personal devices powered by machine learning. Yet, machine learning has proven to be vulnerable to adversarial examples. A large number of modern systems protect…

Machine learning approaches for speech enhancement are becoming increasingly expressive, enabling ever more powerful modifications of input signals. In this paper, we demonstrate that this expressiveness introduces a vulnerability: advanced…

Recent studies have highlighted audio adversarial examples as a ubiquitous threat to state-of-the-art automatic speech recognition systems. Thorough studies on how to effectively generate adversarial examples are essential to prevent…

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…

Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by…

Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems. However, recent research on adversarial examples poses enormous challenges on the robustness of…

Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data.…

Audio DeepFakes (DF) are artificially generated utterances created using deep learning, with the primary aim of fooling the listeners in a highly convincing manner. Their quality is sufficient to pose a severe threat in terms of security…

Speech emotion recognition (SER) is constantly gaining attention in recent years due to its potential applications in diverse fields and thanks to the possibility offered by deep learning technologies. However, recent studies have shown…

Speaker verification systems have been widely used in smart phones and Internet of things devices to identify legitimate users. In recent work, it has been shown that adversarial attacks, such as FAKEBOB, can work effectively against…

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.…

In this paper, we evaluate deep learning-enabled AED systems against evasion attacks based on adversarial examples. We test the robustness of multiple security critical AED tasks, implemented as CNNs classifiers, as well as existing…

Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to detect the presence of adversarial examples, i.e., a binary…

Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adversarial attack algorithms on five deep learning models…

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…

A number of studies have successfully developed speaker verification or presentation attack detection systems. However, studies integrating the two tasks remain in the preliminary stages. In this paper, we propose two approaches for…

High-performance anti-spoofing models for automatic speaker verification (ASV), have been widely used to protect ASV by identifying and filtering spoofing audio that is deliberately generated by text-to-speech, voice conversion, audio…

In this paper we demonstrate that performance of a speaker verification system can be improved by concatenating electroencephalography (EEG) signal features with speech signal features or only using EEG signal features. We use…

Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model,…

Automatic speaker verification, like every other biometric system, is vulnerable to spoofing attacks. Using only a few minutes of recorded voice of a genuine client of a speaker verification system, attackers can develop a variety of…