Related papers: QFA2SR: Query-Free Adversarial Transfer Attacks to…

The emergence of large-scale automatic speech recognition (ASR) models such as Whisper has greatly expanded their adoption across diverse real-world applications. Ensuring robustness against even minor input perturbations is therefore…

Automatic speech recognition (ASR) provides diverse audio-to-text services for humans to communicate with machines. However, recent research reveals ASR systems are vulnerable to various malicious audio attacks. In particular, by removing…

With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it…

Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately. Existing methods often rely on complex modular systems or require extensive fine-tuning…

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…

Adversarial transferability remains a critical challenge in evaluating the robustness of deep neural networks. In security-critical applications, transferability enables black-box attacks without access to model internals, making it a key…

Automatic speech recognition (ASR) systems can be fooled via targeted adversarial examples, which induce the ASR to produce arbitrary transcriptions in response to altered audio signals. However, state-of-the-art adversarial examples…

Membership inference attacks allow adversaries to determine whether a particular example was contained in the model's training dataset. While previous works have confirmed the feasibility of such attacks in various applications, none has…

While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks,…

Automatic Speech Recognition services (ASRs) inherit deep neural networks' vulnerabilities like crafted adversarial examples. Existing methods often suffer from low efficiency because the target phases are added to the entire audio sample,…

Developers need to perform adequate testing to ensure the quality of Automatic Speech Recognition (ASR) systems. However, manually collecting required test cases is tedious and time-consuming. Our recent work proposes CrossASR, a…

Neural networks have become pervasive across various applications, including security-related products. However, their widespread adoption has heightened concerns regarding vulnerability to adversarial attacks. With emerging regulations and…

As speech translation (ST) systems become increasingly prevalent, understanding their vulnerabilities is crucial for ensuring robust and reliable communication. However, limited work has explored this issue in depth. This paper explores…

Although deep-learning based video recognition models have achieved remarkable success, they are vulnerable to adversarial examples that are generated by adding human-imperceptible perturbations on clean video samples. As indicated in…

Deep learning models are susceptible to adversarial samples in white and black-box environments. Although previous studies have shown high attack success rates, coupling DNN models with interpretation models could offer a sense of security…

Voice-enabled commercial products are ubiquitous, typically enabled by lightweight on-device keyword spotting (KWS) and full automatic speech recognition (ASR) in the cloud. ASR systems require significant computational resources in…

Automatic Speaker Recognition Systems (SRSs) have been widely used in voice applications for personal identification and access control. A typical SRS consists of three stages, i.e., training, enrollment, and recognition. Previous work has…

We propose a versatile framework based on random search, Sparse-RS, for score-based sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on substitute models and achieves state-of-the-art success rate and…

Adversarial attacks against commercial black-box speech platforms, including cloud speech APIs and voice control devices, have received little attention until recent years. The current "black-box" attacks all heavily rely on the knowledge…

Recent advances in Automatic Speech Recognition (ASR) have demonstrated remarkable accuracy and robustness in diverse audio applications, such as live transcription and voice command processing. However, deploying these models on…