Related papers: SYSML: StYlometry with Structure and Multitask Lea…

Text mining and information retrieval techniques have been developed to assist us with analyzing, organizing and retrieving documents with the help of computers. In many cases, it is desirable that the authors of such documents remain…

Graph data contains rich node features and unique edge information, which have been applied across various domains, such as citation networks or recommendation systems. Graph Neural Networks (GNNs) are specialized for handling such data and…

In our paper we explore the definition, and extrapolation of fallacies as they pertain to the automatic detection of manipulation on social media. In particular we explore how these logical fallacies might appear in the real world i.e…

These days different platforms such as social media provide their clients from different backgrounds and languages the possibility to connect and exchange information. It is not surprising anymore to see comments from different languages in…

Text Recognition (TR) refers to the research area that focuses on retrieving textual information from images, a topic that has seen significant advancements in the last decade due to the use of Deep Neural Networks (DNN). However, these…

Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers. In this paper, we propose a new regularization scheme based on token-level…

To preserve anonymity and obfuscate their identity on online platforms users may morph their text and portray themselves as a different gender or demographic. Similarly, a chatbot may need to customize its communication style to improve…

Social media platforms such as Twitter are filled with social spambots. Detecting these malicious accounts is essential, yet challenging, as they continually evolve and evade traditional detection techniques. In this work, we propose VASSL,…

This paper reviews the Sybil attack in social networks, which has the potential to compromise the whole distributed network. In the Sybil attack, the malicious user claims multiple identities to compromise the network. Sybil attacks can be…

Tor and i2p networks are two of the most popular darknets. Both darknets have become an area of illegal activities highlighting the necessity to study and analyze them to identify and report illegal content to Law Enforcement Agencies…

Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-imbalanced data where only a few samples are annotated. Existing solutions typically require substantial cost to solve complex optimization problems, or class-balanced…

There is an increasing interest in ensuring machine learning (ML) frameworks behave in a socially responsible manner and are deemed trustworthy. Although considerable progress has been made in the field of Trustworthy ML (TwML) in the…

Mining the silent members of an online community, also called lurkers, has been recognized as an important problem that accompanies the extensive use of online social networks (OSNs). Existing solutions to the ranking of lurkers can aid…

The training of topic models for a multilingual environment is a challenging task, requiring the use of sophisticated algorithms, topic-aligned corpora, and manual evaluation. These difficulties are further exacerbated when the developer…

Deep Neural Networks (DNNs) are increasingly deployed in safety-critical applications including autonomous vehicles and medical diagnostics. To reduce the residual risk for unexpected DNN behaviour and provide evidence for their trustworthy…

Symbolic regression (SR) is a powerful technique for discovering the underlying mathematical expressions from observed data. Inspired by the success of deep learning, recent deep generative SR methods have shown promising results. However,…

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal…

Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks. Currently, there are two popular approaches to make use of…

Pre-trained Transformers are challenging human performances in many NLP tasks. The massive datasets used for pre-training seem to be the key to their success on existing tasks. In this paper, we explore how a range of pre-trained Natural…

Large Language Model (LLM) alignment aims to ensure that LLM outputs match with human values. Researchers have demonstrated the severity of alignment problems with a large spectrum of jailbreak techniques that can induce LLMs to produce…