654 citations
- Centre for Quantum TechnologiesSG36 papers
- National University of SingaporeSG36 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di CataniaIT31 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di MilanoIT20 papers
- Nanyang Technological UniversitySG19 papers
- University of MilanIT19 papers
- Forschungszentrum JülichDE18 papers
- Universitat de BarcelonaES17 papers
- Université Grenoble AlpesFR17 papers
- Centre National de la Recherche ScientifiqueFR16 papers
- European Organization for Nuclear ResearchCH16 papers
- Khalifa University of Science and TechnologyAE16 papers
14 papers · 1 filter
From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
Mohamed Amine Ferrag, Norbert Tihanyi, Djallel Hamouda +3
Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration.…
Trustworthy Intrusion Detection: Confidence Estimation Using Latent Space
Ioannis Pitsiorlas, George Arvanitakis, Marios Kountouris
This work introduces a novel method for enhancing confidence in anomaly detection in Intrusion Detection Systems (IDS) through the use of a Variational Autoencoder (VAE) architectu…
Reverse Engineered MiniFS File System
Dmitrii Belimov, Evgenii Vinogradov
In an era where digital connectivity is increasingly foundational to daily life, the security of Wi-Fi Access Points (APs) is a critical concern. This paper addresses the vulnerabi…
ESASCF: Expertise Extraction, Generalization and Reply Framework for an Optimized Automation of Network Security Compliance
Mohamed C. Ghanem, Thomas M. Chen, Mohamed A. Ferrag +1
The Cyber threats exposure has created worldwide pressure on organizations to comply with cyber security standards and policies for protecting their digital assets. Vulnerability a…
SoK: A Systematic Review of TEE Usage for Developing Trusted Applications
Arttu Paju, Muhammad Owais Javed, Juha Nurmi +3
Trusted Execution Environments (TEEs) are a feature of modern central processing units (CPUs) that aim to provide a high assurance, isolated environment in which to run workloads t…
Towards Automated Detection of Single-Trace Side-Channel Vulnerabilities in Constant-Time Cryptographic Code
Ferhat Erata, Ruzica Piskac, Victor Mateu +1
Although cryptographic algorithms may be mathematically secure, it is often possible to leak secret information from the implementation of the algorithms. Timing and power side-cha…