相关论文: Exploring Targeted Universal Adversarial Perturbat…

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…

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Nevertheless, existing…

In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block,…

End-to-end (E2E) automatic speech recognition (ASR) systems directly map acoustics to words using a unified model. Previous works mostly focus on E2E training a single model which integrates acoustic and language model into a whole.…

Vision-language pre-trained (VLP) models have been the foundation of numerous vision-language tasks. Given their prevalence, it becomes imperative to assess their adversarial robustness, especially when deploying them in security-crucial…

Social networks have become an indispensable part of our lives, with billions of people producing ever-increasing amounts of text. At such scales, content policies and their enforcement become paramount. To automate moderation, questionable…

Owing to the susceptibility of deep learning systems to adversarial attacks, there has been a great deal of work in developing (both empirically and certifiably) robust classifiers. While most work has defended against a single type of…

In this work, we make two contributions towards understanding of in-context learning of linear models by transformers. First, we investigate the adversarial robustness of in-context learning in transformers to hijacking attacks -- a type of…

Accent variability has posed a huge challenge to automatic speech recognition~(ASR) modeling. Although one-hot accent vector based adaptation systems are commonly used, they require prior knowledge about the target accent and cannot handle…

The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained…

In communication systems, there are many tasks, like modulation recognition, which rely on Deep Neural Networks (DNNs) models. However, these models have been shown to be susceptible to adversarial perturbations, namely imperceptible…

The speech enhancement task usually consists of removing additive noise or reverberation that partially mask spoken utterances, affecting their intelligibility. However, little attention is drawn to other, perhaps more aggressive signal…

Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data. A standard way to address this issue is with shallow fusion methods at inference time. However, due…

Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the…

The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of universal adversarial perturbations (UAPs), i.e. a single…

We introduce a method for learning adversarial perturbations targeted to individual images or videos. The learned perturbations are found to be sparse while at the same time containing a high level of feature detail. Thus, the extracted…

Modern Voice Control Systems (VCS) rely on the collaboration of Automatic Speech Recognition (ASR) and Speaker Recognition (SR) for secure interaction. However, prior adversarial attacks typically target these tasks in isolation,…

Advantages of deep learning over traditional methods have been demonstrated for radio signal classification in the recent years. However, various researchers have discovered that even a small but intentional feature perturbation known as…

Proper nouns present a challenge for end-to-end (E2E) automatic speech recognition (ASR) systems in that a particular name may appear only rarely during training, and may have a pronunciation similar to that of a more common word. Unlike…

Precision matrix estimation is a fundamental topic in multivariate statistics and modern machine learning. This paper proposes an adversarially perturbed precision matrix estimation framework, motivated by recent developments in adversarial…