5 papers
Treating the Model as an Untrusted Component: Deterministic Policy Enforcement, Human Approval and Taint Tracking Against Prompt Injection in Tool-Using Agents, with Validation on Open-Weights Models
Mustafa S. Aljumaily, Nawar S. Alseelawi, Raghad Alshabandar
Tool-using LLM agents act on instructions embedded in the data they read, so prompt injection is a structural rather than a prompt-wording problem. We compare in-prompt defences (h…
Qistas: A Pre-Registered, Portable Protocol for Fairness Evaluation of Large Language Models
Nawar S. Alseelawi, Mustafa S. Aljumaily
Fairness benchmarks for large language models (LLMs) are overwhelmingly English-born and American in their social categories; translated versions carry those categories into societ…
PVBRF-ID: Private, Verifiable and Byzantine-Robust Federated Intrusion Detection for Oilfield Enterprise Networks
Mustafa S. Aljumaily, Ali Ataeemh Allami, Mustafa N. Mnati +2
Federated learning allows dispersed oilfield sites to train a shared intrusion detector without pooling network traffic, yet its aggregation step forces a choice between privacy an…
Attributing Sensor Deviations to Degradation, Weather, or Attack in Oilfield Digital Twins: A Simulation Study of Probabilistic Attribution and Cost-Based Decisions
Mustafa S. Aljumaily, Nawar S. Alseelawi, Hayder Kareem Abed
When an oilfield digital twin disagrees with its instruments, the operator must decide whether the cause is hardware degradation, harsh-weather effects, or malicious data manipulat…
Toward Responsible AI-Augmented Cyber Defense: Pattern Recognition, Defense-in-Depth, and the Case for Human-AI Collaboration
Mustafa S. Aljumaily, Hayder Kareem Abed, Nawar S. Alseelawi
Cybersecurity literature has extensively documented the operational benefits of artificial intelligence (AI) for threat detection, incident response, and prevention, while raising…