相关论文: Addressing Topic Leakage in Cross-Topic Evaluation…

Recently, it has been shown that Machine Learning models can leak sensitive information about their training data. This information leakage is exposed through membership and attribute inference attacks. Although many attack strategies have…

Automatic short answer grading (ASAG) techniques are designed to automatically assess short answers to questions in natural language, having a length of a few words to a few sentences. Supervised ASAG techniques have been demonstrated to be…

As pointed out by several scholars, current research on hate speech (HS) recognition is characterized by unsystematic data creation strategies and diverging annotation schemata. Subsequently, supervised-learning models tend to generalize…

Authorship Verification (AV) is a key area of research in digital text forensics, which addresses the fundamental question of whether two texts were written by the same person. Numerous computational approaches have been proposed over the…

In today's data-driven world, the proliferation of publicly available information raises security concerns due to the information leakage (IL) problem. IL involves unintentionally exposing sensitive information to unauthorized parties via…

Textual noise, such as typos or abbreviations, is a well-known issue that penalizes vanilla Transformers for most downstream tasks. We show that this is also the case for sentence similarity, a fundamental task in multiple domains, e.g.…

Patch robustness certification is an emerging kind of provable defense technique against adversarial patch attacks for deep learning systems. Certified detection ensures the detection of all patched harmful versions of certified samples,…

Traffic accident forecasting is a significant problem for transportation management and public safety. However, this problem is challenging due to the spatial heterogeneity of the environment and the sparsity of accidents in space and time.…

Authorship attribution (AA) is the task of identifying the most likely author of a query document from a predefined set of candidate authors. We introduce a two-stage retrieve-and-rerank framework that finetunes LLMs for cross-genre AA.…

The widespread of fake news and misinformation in various domains ranging from politics, economics to public health has posed an urgent need to automatically fact-check information. A recent trend in fake news detection is to utilize…

For practical automatic speaker verification (ASV) systems, replay attack poses a true risk. By replaying a pre-recorded speech signal of the genuine speaker, ASV systems tend to be easily fooled. An effective replay detection method is…

This study investigates the applicability of authorship attribution based on stylistic features to support actor analysis in threat intelligence. As a foundational step toward future application to dark web forums, we conducted experiments…

Meeting transcription is a field of high relevance and remarkable progress in recent years. Still, challenges remain that limit its performance. In this work, we extend a previously proposed framework for analyzing leakage in speech…

As large-scale, pre-trained language models achieve human-level and superhuman accuracy on existing language understanding tasks, statistical bias in benchmark data and probing studies have recently called into question their true…

The ubiquity of offensive and hateful content on online fora necessitates the need for automatic solutions that detect such content competently across target groups. In this paper we show that text classification models trained on large…

Dataset ownership verification, the process of determining if a dataset is used in a model's training data, is necessary for detecting unauthorized data usage and data contamination. Existing approaches, such as backdoor watermarking, rely…

Stopping the malicious spread and production of false and misleading news has become a top priority for researchers. Due to this prevalence, many automated methods for detecting low quality information have been introduced. The majority of…

A new method for visualizing the relatedness of scientific areas is developed that is based on measuring the overlap of researchers between areas. It is found that closely related areas have a high propensity to share a larger number of…

Consider a scenario where an author-e.g., activist, whistle-blower, with many public writings wishes to write "anonymously" when attackers may have already built an authorship attribution (AA) model based off of public writings including…

Supervised classification heavily depends on datasets annotated by humans. However, in subjective tasks such as toxicity classification, these annotations often exhibit low agreement among raters. Annotations have commonly been aggregated…