Related papers: OpenFact at CheckThat! 2024: Combining Multiple At…

Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in…

Real-world natural language processing systems need to be robust to human adversaries. Collecting examples of human adversaries for training is an effective but expensive solution. On the other hand, training on synthetic attacks with small…

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

Adversarial attacks are label-preserving modifications to inputs of machine learning classifiers designed to fool machines but not humans. Natural Language Processing (NLP) has mostly focused on high-level attack scenarios such as…

While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among…

Adversarial training (AT) as a regularization method has proved its effectiveness in various tasks, such as image classification and text classification. Though there are successful applications of AT in many tasks of natural language…

This paper describes our approach to the task of identifying offensive languages in a multilingual setting. We investigate two data augmentation strategies: using additional semi-supervised labels with different thresholds and cross-lingual…

Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A common way to improve model robustness is adversarial training…

Large pre-trained language representation models (LMs) have recently collected a huge number of successes in many NLP tasks. In 2018 BERT, and later its successors (e.g. RoBERTa), obtained state-of-the-art results in classical benchmark…

Online fake news profoundly distorts public judgment and erodes trust in social platforms. While existing detectors achieve competitive performance on benchmark datasets, they remain notably vulnerable to malicious comments designed…

In targeted adversarial attacks on vision models, the selection of the target label is a critical yet often overlooked determinant of attack success. This target label corresponds to the class that the attacker aims to force the model to…

This paper presents the different models submitted by the LT@Helsinki team for the SemEval 2020 Shared Task 12. Our team participated in sub-tasks A and C; titled offensive language identification and offense target identification,…

Adversarial training can improve the robustness of neural networks. Previous methods focus on a single adversarial training strategy and do not consider the model property trained by different strategies. By revisiting the previous methods,…

Neural models based on pre-trained transformers, such as BERT or XLM-RoBERTa, demonstrate SOTA results in many NLP tasks, including non-topical classification, such as genre identification. However, often these approaches exhibit low…

To combat adversarial spelling mistakes, we propose placing a word recognition model in front of the downstream classifier. Our word recognition models build upon the RNN semi-character architecture, introducing several new backoff…

Self-supervised learning approach like contrastive learning is attached great attention in natural language processing. It uses pairs of training data augmentations to build a classification task for an encoder with well representation…

We extend BeamAttack, an adversarial attack algorithm designed to evaluate the robustness of text classification systems through word-level modifications guided by beam search. Our extensions include support for word deletions and the…

Healthcare predictive analytics aids medical decision-making, diagnosis prediction and drug review analysis. Therefore, prediction accuracy is an important criteria which also necessitates robust predictive language models. However, the…

Beyond the success story of adversarial training (AT) in the recent text domain on top of pre-trained language models (PLMs), our empirical study showcases the inconsistent gains from AT on some tasks, e.g. commonsense reasoning, named…

In recent years, deep learning has shown itself to be an incredibly valuable tool in cybersecurity as it helps network intrusion detection systems to classify attacks and detect new ones. Adversarial learning is the process of utilizing…