|
11:00 – 12:00
|
Presentations Session
|
|
Presentations on various topics related to the workshop theme. Each presentation will be alloted a total of 15 minutes and will be followed by a brief Q&A session of 5 minutes.
|
|
11:00 – 11:20
|
Exploring Artificial Intelligence Challenges for Monitoring Cyber Child Abuse
|
|
Authors:
Vita Santa Barletta, Danilo Caivano, Giovanni Dimauro, Francesca Mantini, Massimiliano Morga
|
|
Presented by:
Francesca Mantini
(University of Bari Aldo Moro, Italy)
|
|
Abstract:
The growing phenomenon of online production and dissemination of child sexual abuse material (CSAM - Child Sexual Abuse Material) poses increasingly complex challenges for law enforcement agencies in the area of online safety and child protection. Online Child Sexual Abuse (OCSA) emerges as a major threat in an increasingly digitalized world. It is estimated that more than one billion children between the ages of 2 and 17 are sexually abused each year, a figure that probably underestimates the true extent of the phenomenon, as most violence goes unreported to the relevant authorities. The situation is further exacerbated by the proliferation of dark web platforms that, lacking moderation, provide fertile ground for these crimes, making the task of tracing the origin of abuse extremely difficult and demonstrating how new methods of detection are needed.
Based on these premises, this paper aims to conduct an in-depth analysis of the literature regarding current machine learning models for the detection of images, videos and texts containing CSA, evaluating their effectiveness, limitations, and ethical implications.
|
|
|
11:20 – 11:40
|
LLMs to Detect Cyber Child Abuse in the in Textual Conversations
|
|
Authors:
Maria Teresa Baldassarre, Vita Santa Barletta, Vito Bavaro, Danilo Caivano, Alberto Pio De Matteis, Andrea Lippolis, Antonio Piccinno
|
|
Presented by:
Vita Santa Barletta
(University of Bari Aldo Moro, Italy)
|
|
Abstract:
In contemporary online interactions, identifying inappropriate language and safeguarding minors from harmful communication is a critical challenge. This study explores the use of Large Language Models (LLMs) to analyze text, detecting patterns indicative of age-specific language and the presence of sexual or pornographic references. A fine-tuning of the LLaMAntino model was performed, using a dataset of synthetically generated sentences designed to replicate real-world scenarios. The fine-tuned model demonstrated enhanced performance compared to its baseline (given by LLaMAntino 3 ANITA 8B), providing detailed and context-sensitive explanations for its classifications.
The results highlight the potential of LLMs in addressing sensitive linguistic phenomena with precision, offering a foundation for detecting indirect combinations of sexual references in conversations involving minors. Future work can focus on incorporating real conversational data and involving subject matter experts to refine the model’s interpretability and reliability. Additionally, the exploration of advanced architectures and fine-tuning techniques will be considered to further balance model complexity and processing efficiency.
|
|
|
11:40 – 12:00
|
Bridging the Gap between Knowledge and Human Expertise: Integrating Explicit and Tacit Knowledge in Maintenance Operations
|
|
Authors:
Ignacio Aedo, Teresa Onorati, Cesare Tucci, Paloma Díaz, Alvaro Montero, Juan Castro
|
|
Presented by:
Paloma Diaz
(Universidad Carlos III de Madrid, Spain)
|
|
Abstract:
Knowledge transfer is crucial in establishing an institutional memory that guarantees informed decisions, continuity, and improved productivity and efficiency. It enables sharing best practices and insights among individual workers and teams, and creates collective and sustainable capabilities. However, effective knowledge transfer leads to several challenges in capturing and sharing the knowledge of more experienced workers, primarily what is known as tacit knowledge, due to inadequate technological support and cultural and organizational barriers. This paper proposes overcoming these obstacles with a technological solution based on the Knowledge-Assisted Visual Analytics model to collect and share explicit and tacit knowledge while interacting with a visual information system. We tested the validity of our approach in a real use case designed in collaboration with the Spanish Army and affecting two different maintenance parks. The Visual Analytics tool creates a unique knowledge base that centralizes all the knowledge about maintenance operations and includes both the explicit knowledge included in a set of official, though incomplete, handbooks and the tacit knowledge operators have developed over time. This tacit knowledge is captured in two ways due to the differences in the parks, the material, and the personnel involved. In one case, it is externalized using videos, whilst in the other, we relied upon a focus group where experts usually discuss unclear parts of the handbooks or tricks to be more efficient.
|
|