The 2024 doctoral fellowship from the LIA has been awarded to the Cornet team. Several topics have been proposed, and they are available on the Adum platform. In alphabetical order by title: Interested candidates should apply on the Adum platform. Most importantly, before doing so, contact the researchers who propose the topics to discuss them further.
The next seminar of the Cornet team will take place on February 23, 2024, at 11:35 a.m. in S3, and will consist of two parts. First, Sylvie Chaddad (LIA) will present her thesis topic on Stochastic Control for Optimizing Crowdfunding Project Dynamics. Then, Lorena Garrido (University of Veracruz) will present her work titled On the Monge-Kantorovich divergence. Abstract: The Monge-Kantorovich divergence is a measure of closeness between probability distributions. Historically, it arises from an optimal transport problem of sand movement, in the area of civil engineering. Today, the Monge-Kantorovich problem has given rise to many theoretical studies, as well as various applications, including data analysis. In this talk, a couple of applications in data analysis will be mentioned.
The next seminar of the Cornet team will take place on January 31, 2024, at 11:35 am in S3 and will consist of two parts. Firstly, Felipe Albuquerque (LIA) will present his thesis topic on ‘The p-Median Problem with Coverage Constraints: New Resolution Methods and Application to the Design of Public Services.’ Following that, Luca Dini and Pierre Jourlin will present their ongoing work on the theme of ‘Hybrid Methods for Cognitive Attitudes Detection.’ Summary: In this seminar, we will present ongoing work on the transformation of a keyword spotting system into a concept-based labeling engine. We will highlight four major axes of this work:
On Friday, January 19th, at 11:35 in room S6, we will have three short presentations:
Date: Thursday, January 18, 2023 at 14:00. Place: University of Avignon, Campus JH Fabre, Ada Lovelace amphitheater Jury : Title: Combining Graph and Text to Model Conversations: An Application to Online Abuse Detection. Abstract: Online abusive behaviors can have devastating consequences on individuals and communities. With the global expansion of internet and the social networks, anyone can be confronted with these behaviors. Over the past few years, laws and regulations have been established to regulate this kind of abuse but the responsibility ultimately lies with the platforms that host online communications. They are asked to monitor their users in order to prevent the proliferation of abusive content. Timely detection and moderation is a key factor to reduce the quantity and impact of abusive behaviors. However, due to the sheer quantity of online messages posted every day, platforms struggle to provide adequate resources. Since this implies high human and financial costs, companies have a keen interest in automating this process. Although it may seem a relatively simple task, it turns out to be quite complex. Indeed, malicious users have developed numerous techniques to bypass the standard automated methods. Allusions or implied meaning are other examples of strategies that automatic methods struggle Plus d'infos
Planning And leaRning For AI-Edge compuTing Partners: Period: 2023-2027
General information: Context: Cyber deception is a defense strategy, complementary to conventional approaches, used to enhance the security posture of a system. The basic idea of this technique is to deliberately conceal and/or falsify a part of such system by deploying and managing decoys (e.g., “honeypots”, “honeynets”, etc.), i.e., applications, data, network elements and protocols that appear to malicious actors as a legitimate part of the system, and to which their attacks are misdirected. The advantage of an effective cyber deception strategy is twofold: on one hand, it depletes attackers’ resources while allowing system security tools to take necessary countermeasures; on the other hand, it provides valuable insights on attackers’ tactics and techniques, which can be used to improve system’s resilience to future attacks and upgrade security policies accordingly. Although cyber-deception has been successfully applied in some scenarios, existing deception approaches lack the flexibility to be seamlessly operated in highly distributed and resource-constrained environments. Indeed, if virtualization and cloud-native design approaches paved the way for ubiquitous deployment of applications, they widened the attack surface that malicious actors might exploit. In such a scenario, it is practically unfeasible to try to deploy decoys for each and every system’s service or application Plus d'infos
Context: Large scale problems exist for the electricity system both for short-term (e.g., the Unit Commitment problem) and long-term (system planning, e.g. ”Generation Expansion Planning”). In these problems concerning the modern and future electricity system, the question of the integration of energy consumption flexibility is crucial. This flexibility, consisting in “optimally” scheduling the power profile of particular electrical appliances (the most common and suitable ones for that purpose being Electric Vehicles (EV) and Water-Heaters (WH) for residential consumers), allows obtaining a supply-demand equilibrium with diminished total system cost, in comparison to the case where only production assets are controllable. Considering flexibilities related to “small” individual con- sumers (again, EV or WH), their very large number makes it inappropriate to model them individually in the typical electricity system optimization problems, for tractability reasons: it thus seems relevant to consider an aggregate model of consumption flexibilities. In turn, the question of the “right level” of aggregation modelling is of particular importance. Aggregation/disaggregation techniques are widely studied in the context of smart grids. Objective: More precisely, the objective of this internship is to study, on a simple example, the impact of aggregation techniques and aggregation levels, and to solve an optimal energy scheduling Plus d'infos
Pang (Pattern-Based Anomaly Detection in Graphs) is an algorithm which represents and classifies a collection of graphs according to their frequent patterns (subgraphs). The detail of this algorithm are described in the below article. This work was conducted in the framework of the DeCoMaP ANR project (Detection of corruption in public procurement markets — ANR-19-CE38-0004). Plus d'infos
The Revised Database of Elected Officials in France (BRÉF) is built from a primary source, the National Directory of Elected Officials (RNE), along with several secondary sources, including databases from the National Assembly, the Senate, and the European Parliament. The intention is to expand this database further by fully leveraging these secondary sources and, in the longer term, by integrating new databases and occasional contributions.
Laboratoire Informatique d'Avignon — Avignon Université