Related papers: Phrase-Level Adversarial Training for Mitigating B…

In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…

This paper proposes a black-box adversarial attack method to automatic speech recognition systems. Some studies have attempted to attack neural networks for speech recognition; however, these methods did not consider the robustness of…

Though deep neural networks have achieved state-of-the-art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to…

Adversarial training is a common approach for bias mitigation in natural language processing. Although most work on debiasing is motivated by equal opportunity, it is not explicitly captured in standard adversarial training. In this paper,…

Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches to training robust models against…

Passwords remain one of the most common methods for securing sensitive data in the digital age. However, weak password choices continue to pose significant risks to data security and privacy. This study aims to solve the problem by focusing…

Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…

Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make…

In recent years, pre-trained models have become dominant in most natural language processing (NLP) tasks. However, in the area of Automated Essay Scoring (AES), pre-trained models such as BERT have not been properly used to outperform other…

It has been demonstrated that deep neural networks are prone to noisy examples particular adversarial samples during inference process. The gap between robust deep learning systems in real world applications and vulnerable neural networks…

Machine learning models are usually evaluated according to the average case performance on the test set. However, this is not always ideal, because in some sensitive domains (e.g. autonomous driving), it is the worst case performance that…

Grammatical Error Correction (GEC) systems perform a sequence-to-sequence task, where an input word sequence containing grammatical errors, is corrected for these errors by the GEC system to output a grammatically correct word sequence.…

Adversarial attacks are carried out to reveal the vulnerability of deep neural networks. Textual adversarial attacking is challenging because text is discrete and a small perturbation can bring significant change to the original input.…

Recent advancements in natural language processing have highlighted the vulnerability of deep learning models to adversarial attacks. While various defence mechanisms have been proposed, there is a lack of comprehensive benchmarks that…

Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily…

Machine learning models are vulnerable to maliciously crafted Adversarial Examples (AEs). Training a machine learning model with AEs improves its robustness and stability against adversarial attacks. It is essential to develop models that…

This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algorithms achieve high prediction performance, they are…

Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the victim model is…

Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction…

Automatic essay grading (AEG) has attracted the the attention of the NLP community because of its applications to several educational applications, such as scoring essays, short answers, etc. AEG systems can save significant time and money…