Sommaire

  • Cet exposé a été présenté le 20 mai 2025 (11:00 - 12:00).

Description

  • Orateur

    Manuel Maarek - Heriot-Watt University

Creating secure software code requires software engineers to elicit and 
follow the security requirements of the system they are building. 
Software engineer teams might not have the security expertise to 
approach this angle of software development confidently. With the 
democratisation of access to software development and deployment, 
software are often built by developers with neither software engineering 
expertise nor security knowledge, a situation that could make systems 
vulnerable. We present approaches based on short games, knowledge cards 
and serious game jams designed to help these non-experts gain the 
knowledge and ability to communicate on code security. These are some of 
the outputs of the Secrious project published recently in the IEEE 
Security & Privacy magazine, and in the ACM Games and Computer Standards 
& Interfaces journals. The project was supported by the Engineering and 
Physical Research Council (Grant EP/T017511/1 "Serious Coding: A Game 
Approach To Security For The New Code-Citizens"). 

Manuel Maarek from Heriot-Watt University is visiting the Université de 
Rennes/IRISA as part of the MLSEAN Machine Learning based software 
systems SEcurity ANalysis project supported by the UK-France Science, 
Innovation, and Technology Researcher Mobility Scheme.

Infos pratiques

Prochains exposés

  • Opening Pandora's Box: White-Box Attacks on Microsoft's PhotoDNA Perceptual Hash Function

    • 05 juin 2026 (11:00 - 12:00)

    • Inria Center of the University of Rennes - Aurigny room

    Orateur : Diane Leblanc-Albarel - KU Leuven

    PhotoDNA is a widely deployed perceptual hash function used for the detection of illicit content such as Child Sexual Abuse Material (CSAM). In this talk, I will present our paper introducing the first mathematical description of Alleged PhotoDNA, a function that reproduces the outputs of PhotoDNA. Our analysis reveals several structural weaknesses: the function is piece-wise linear and[…]

    • Cryptography

    • Privacy

  • Towards More Secure Large Language Models

    • 12 juin 2026 (11:00 - 12:00)

    • Inria Center of the University of Rennes - Petri/Turing room

    Orateur : Raouf Kerkouche - Inria Lille

    Large Language Models (LLMs) have achieved considerable success and are now widely used across multiple domains, highlighting their transformative impact on both technology and society. However, this widespread adoption also exposes LLMs to numerous security threats that can alter model behavior or degrade overall performance. To mitigate these threats, most research has focused on alignment[…]

    • Machine learning

Voir les exposés passés
Haut de page