相关论文: Forging the Forger: An Attempt to Improve Authorsh…

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…

We present FireBERT, a set of three proof-of-concept NLP classifiers hardened against TextFooler-style word-perturbation by producing diverse alternatives to original samples. In one approach, we co-tune BERT against the training data and…

Solving math problems through verifiable languages such as Lean has significantly impacted both the mathematics and computer science communities. Current state-of-the-art models are often trained with expensive online Reinforcement Learning…

We explore the use of deep reinforcement learning to audit an automatic short answer grading (ASAG) model. Automatic grading may decrease the time burden of rating open-ended items for educators, but a lack of robust evaluation methods for…

We propose to improve text recognition from a new perspective by separating the text content from complex backgrounds. As vanilla GANs are not sufficiently robust to generate sequence-like characters in natural images, we propose an…

Optimizing the phrasing of argumentative text is crucial in higher education and professional development. However, assessing whether and how the different claims in a text should be revised is a hard task, especially for novice writers. In…

We study two important concepts in adversarial deep learning---adversarial training and generative adversarial network (GAN). Adversarial training is the technique used to improve the robustness of discriminator by combining adversarial…

By utilizing more computational resources at test-time, large language models (LLMs) can improve without additional training. One common strategy uses verifiers to evaluate candidate outputs. In this work, we propose a novel scaling…

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…

The rise of language models such as BERT allows for high-quality text paraphrasing. This is a problem to academic integrity, as it is difficult to differentiate between original and machine-generated content. We propose a benchmark…

Adversarial attacks are often considered as threats to the robustness of Deep Neural Networks (DNNs). Various defending techniques have been developed to mitigate the potential negative impact of adversarial attacks against task…

An ever-growing body of work has demonstrated the rich information content available in eye movements for user modelling, e.g. for predicting users' activities, cognitive processes, or even personality traits. We show that state-of-the-art…

To improve policy robustness of deep reinforcement learning agents, a line of recent works focus on producing disturbances of the environment. Existing approaches of the literature to generate meaningful disturbances of the environment are…

We consider technology-assisted mimicry attacks in the context of automatic speaker verification (ASV). We use ASV itself to select targeted speakers to be attacked by human-based mimicry. We recorded 6 naive mimics for whom we select…

The ability to revise in response to feedback is critical to students' writing success. In the case of argument writing in specific, identifying whether an argument revision (AR) is successful or not is a complex problem because AR quality…

In this study, we implement a novel BERT architecture for multitask fine-tuning on three downstream tasks: sentiment classification, paraphrase detection, and semantic textual similarity prediction. Our model, Multitask BERT, incorporates…

Adversarial purification using generative models demonstrates strong adversarial defense performance. These methods are classifier and attack-agnostic, making them versatile but often computationally intensive. Recent strides in diffusion…

Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However,…

Now-a-days, speech-based biometric systems such as automatic speaker verification (ASV) are highly prone to spoofing attacks by an imposture. With recent development in various voice conversion (VC) and speech synthesis (SS) algorithms,…

Authorship verification (AV) is the task of determining whether two texts were written by the same author and has been studied extensively, predominantly for English data. In contrast, large-scale benchmarks and systematic evaluations for…