arXiv subjects

Djallel Hamouda

Publications and source records attributed to Djallel Hamouda.

3 recordsLinked to original sources

arXiv2025

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and inter-agent protocols has outpaced security practices, leading to brittle integrations that rely on ad-hoc authentication, inconsistent schemas, and weak validation. This survey introduces a unified end-to-end threat model for LLM-agent ecosystems, covering host-to-tool and agent-to-agent communications. We systematically categorize more than thirty attack techniques spanning input manipulation, model compromise, system and privacy attacks, and protocol-level vulnerabilities. For each category, we provide a formal threat formulation defining attacker capabilities, objectives, and affected system layers. Representative examples include Prompt-to-SQL injections and the Toxic Agent Flow exploit in GitHub MCP servers. We analyze attack feasibility, review existing defenses, and discuss mitigation strategies such as dynamic trust management, cryptographic provenance tracking, and sandboxed agent interfaces. The framework is validated through expert review and cross-mapping with real-world incidents and public vulnerability repositories, including CVE and NIST NVD. Compared to prior surveys, this work presents the first integrated taxonomy bridging input-level exploits and protocol-layer vulnerabilities in LLM-agent ecosystems, offering actionable guidance for designing secure and resilient agentic AI systems.

cs.CR↗

arXiv2023

Edge Learning for 6G-enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses

The ongoing deployment of the fifth generation (5G) wireless networks constantly reveals limitations concerning its original concept as a key driver of Internet of Everything (IoE) applications. These 5G challenges are behind worldwide efforts to enable future networks, such as sixth generation (6G) networks, to efficiently support sophisticated applications ranging from autonomous driving capabilities to the Metaverse. Edge learning is a new and powerful approach to training models across distributed clients while protecting the privacy of their data. This approach is expected to be embedded within future network infrastructures, including 6G, to solve challenging problems such as resource management and behavior prediction. This survey article provides a holistic review of the most recent research focused on edge learning vulnerabilities and defenses for 6G-enabled IoT. We summarize the existing surveys on machine learning for 6G IoT security and machine learning-associated threats in three different learning modes: centralized, federated, and distributed. Then, we provide an overview of enabling emerging technologies for 6G IoT intelligence. Moreover, we provide a holistic survey of existing research on attacks against machine learning and classify threat models into eight categories, including backdoor attacks, adversarial examples, combined attacks, poisoning attacks, Sybil attacks, byzantine attacks, inference attacks, and dropping attacks. In addition, we provide a comprehensive and detailed taxonomy and a side-by-side comparison of the state-of-the-art defense methods against edge learning vulnerabilities. Finally, as new attacks and defense technologies are realized, new research and future overall prospects for 6G-enabled IoT are discussed.

cs.CR↗

arXiv2023

Generative Adversarial Networks-Driven Cyber Threat Intelligence Detection Framework for Securing Internet of Things

While the benefits of 6G-enabled Internet of Things (IoT) are numerous, providing high-speed, low-latency communication that brings new opportunities for innovation and forms the foundation for continued growth in the IoT industry, it is also important to consider the security challenges and risks associated with the technology. In this paper, we propose a two-stage intrusion detection framework for securing IoTs, which is based on two detectors. In the first stage, we propose an adversarial training approach using generative adversarial networks (GAN) to help the first detector train on robust features by supplying it with adversarial examples as validation sets. Consequently, the classifier would perform very well against adversarial attacks. Then, we propose a deep learning (DL) model for the second detector to identify intrusions. We evaluated the proposed approach's efficiency in terms of detection accuracy and robustness against adversarial attacks. Experiment results with a new cyber security dataset demonstrate the effectiveness of the proposed methodology in detecting both intrusions and persistent adversarial examples with a weighted avg of 96%, 95%, 95%, and 95% for precision, recall, f1-score, and accuracy, respectively.

cs.CR↗