Recent advances in neural information retrieval (IR) models have significantly enhanced
their effectiveness over various IR tasks. The robustness of these models, essential for …

Beyond effectiveness, the robustness of an information retrieval (IR) system is increasingly
attracting attention. When deployed, a critical technology such as IR should not only deliver …

Large Language Models (LLMs) have been applied to build several automation and
personalized question-answering prototypes so far. However, scaling such prototypes to …

A data void is a gap in online information, providing an opportunity for the spread of
disinformation or a data void exploit. We introduce lightweight measures to track the …

Abstract Internal site Search Abuse Promotion (ISAP) is a prevalent Black Hat Search
Engine Optimization (SEO) technique, which exploits the reputation of abused internal …

Optical Character Recognition (OCR) is a widely used tool to extract text from scanned
documents. Today, the state-of-the-art is achieved by exploiting deep neural networks …

Large Language Models have introduced novel opportunities for text comprehension and
generation. Yet, they are vulnerable to adversarial perturbations and data poisoning attacks …

Artificial intelligence (AI)-based technologies are starting to be adopted in the industrial
world in many different contexts and sectors, from health care to the automotive, from …

The remarkable success of neural networks has led to a growing demand for robustness
verification and guarantee. However, the discrete nature of text data processed by language …