Related papers: Alert-ME: An Explainability-Driven Defense Against…

Recent developments in adversarial attacks on deep learning leave many mission-critical natural language processing (NLP) systems at risk of exploitation. To address the lack of computationally efficient adversarial defense methods, this…

Adversarial attacks expose important blind spots of deep learning systems. While word- and sentence-level attack scenarios mostly deal with finding semantic paraphrases of the input that fool NLP models, character-level attacks typically…

Sentiment analysis focuses on identifying the emotional polarity expressed in textual data, typically categorized as positive, negative, or neutral. Hate speech detection, on the other hand, aims to recognize content that incites violence,…

The ubiquity of offensive content on social media is a growing cause for concern among companies and government organizations. Recently, transformer-based models such as BERT, XLNET, and XLM-R have achieved state-of-the-art performance in…

Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning. Variants of this method have been used as regularization mechanisms to achieve SOTA results on NLP benchmarks, and…

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Despite the rapid progress in multimodal models and Large Visual-Language Models (LVLM), they remain highly susceptible to adversarial perturbations, raising serious concerns about their reliability in real-world use. While adversarial…

Deep learning has achieved remarkable success in direction-of-arrival (DOA) estimation. However, recent studies have shown that adversarial perturbations can severely compromise the performance of such models. To address this vulnerability,…

Offensive language detection is an ever-growing natural language processing (NLP) application. This growth is mainly because of the widespread usage of social networks, which becomes a mainstream channel for people to communicate, work, and…

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…

The impressive capabilities of recent generative models to create texts that are challenging to distinguish from the human-written ones can be misused for generating fake news, product reviews, and even abusive content. Despite the…

Text classification systems have been proven vulnerable to adversarial text examples, modified versions of the original text examples that are often unnoticed by human eyes, yet can force text classification models to alter their…

Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we propose a one-off and attack-agnostic Feature Manipulation (FM)-Defense to detect…

In various real-world applications such as machine translation, sentiment analysis, and question answering, a pivotal role is played by NLP models, facilitating efficient communication and decision-making processes in domains ranging from…

State-of-the-art text classification models are becoming increasingly reliant on deep neural networks (DNNs). Due to their black-box nature, faithful and robust explanation methods need to accompany classifiers for deployment in real-life…

Modern infrastructures rely on software systems that remain vulnerable to cyberattacks. These attacks frequently exploit vulnerabilities documented in repositories such as MITRE's Common Vulnerabilities and Exposures (CVE). However, Cyber…

Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial…

We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the discriminative cues present in language, such as semantic or stylistic structure. Each…

The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits of NLP model performance, excelling in a variety of tasks. We cast the spotlight on the underexplored task of Natural Language Inference (NLI), since…

Training robust deep learning models for down-stream tasks is a critical challenge. Research has shown that down-stream models can be easily fooled with adversarial inputs that look like the training data, but slightly perturbed, in a way…