José M. de Fuentes

Université Paris-Saclay — France

Computer Science · Physical Sciences

20h-index1.2kcitations97works0.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

User Authentication and Security Systems(23), Advanced Malware Detection Techniques(20), Privacy-Preserving Technologies in Data(19), Vehicular Ad Hoc Networks (VANETs)(17), Network Security and Intrusion Detection(10)

Publications97 total

Characterizing Cross-Contamination on Multitask Multimodal Large Language Models
Information Systems Frontiers·2025
Detecting Multi-Turn Jailbreak Attacks in Large Language Models via Linear Probes
2025
TELESAFE: Monitoring Energy Consumption for Work-Life Boundaries in Telework
SPIRE - Sciences Po Institutional REpository·2025Open Access
LUMIA: Linear Probing for Unimodal and MultiModal Membership Inference Attacks Leveraging Internal LLM States
Lecture notes in computer science·2025Open Access
LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs
Journal of Information Security and Applications·2025Open Access
bench-MIA: Towards automatic multi-lever benchmark construction for MIA evaluation
SPIRE - Sciences Po Institutional REpository·2025
From Lack of Concerns to Complicity: How Misinformation Concerns Influences Fake News Sharing on WhatsApp via the Partisan Legitimation of Fake News
Social Science Quarterly·2025· 2 citedOpen Access
XAI for safe AI: technical-legal misconceptions and misalignments
SPIRE - Sciences Po Institutional REpository·2025Open Access
LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs
arXiv (Cornell University)·2025Open Access
Measuring Implementation Fidelity for the Gathering of Native Americans (GONA)
American Indian and Alaska Native Mental Health Research·2025Open Access
<i>TELESAFE</i> : Detecting Private/Work Boundary Crossings in Energy Consumption Trails in Telework
Proceedings of the VLDB Endowment·2025
Use of Transfer Learning for Affordable In-Context Fake Review Generation
IEEE Transactions on Big Data·2025· 3 citedOpen Access
reteLLMe: Design Rules for Using Large Language Models to Protect the Privacy of Individuals in Their Textual Contributions
Lecture notes in computer science·2025
Service-Aware Password Risk Meter – Helping Users to Choose Suitable Passwords in Services
Lecture notes in computer science·2025
Nob-MIAs: Non-biased Membership Inference Attacks Assessment on Large Language Models with Ex-Post Dataset Construction
Lecture notes in computer science·2024· 2 citedOpen Access
LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states
arXiv (Cornell University)·2024Open Access
TELESAFE – Détection des franchissements de frontière entre vie privée et vie professionnelle dans les traces de consommation d'énergie en télétravail
SPIRE - Sciences Po Institutional REpository·2024Open Access
Continuous Authentication Leveraging Matrix Profile
2024· 1 cited
Vers une détection des activités privées dans la consommation énergétique en télétravail basée sur le profil matriciel
SPIRE - Sciences Po Institutional REpository·2024Open Access
STRCacheML: A Machine Learning-Assisted Content Caching Policy for Streaming Services
2024· 1 citedOpen Access
page 1 of 5Next →

Frequent Co-authors

Lorena González‐Manzano(29), Ana I. González–Tablas(14), Arturo Ribagorda(10), Pedro Peris‐Lopez(6), Omid Mirzaei(5), Juan Tapiador(5), Luis Hernández Encinas(5), Luis Hernández–Álvarez(4), Carmen Cámara(4), Jorge Blasco(4), Mar Gimenez-Aguilar(3), Guillermo Suárez‐Tangil(3), Jorge López Hernández-Ardieta(3), Benjamín Ramos(3), Agustí Solanas(2), Fatbardh Veseli(2), Sergio Pastrana(2), Esther Palomar(2), Almudena Alcaide(2), Cristina Ramos(2)