The rapid expansion of wireless communication and the Internet of Everything (IoE) has transformed modern technology, necessitating secure and efficient Resource Allocation (RA) to optimize system performance. However, the increasing number of IoE devices introduces security vulnerabilities, particularly from Non-Legitimate Devices (NLDs) that threaten network integrity, data confidentiality, and system availability. This study proposes an RA model based on cyber threat intelligence (CTI) to detect and mitigate malicious devices, integrating a two-state Hidden Markov Model (HMM) for NLD identification and encryption/decryption mechanisms for secure task communication. The model is designed for IoE-Edge fog-based networks, reducing dependency on external cloud servers while leveraging 6G-enabled device clustering for optimized task distribution. A novel CTI-based RA mechanism, namely the Secure-Intelligent Main Task Off-loading Scheduling Algorithm (Sec- i MTOSA), is introduced to enhance intelligent scheduling and secure RA. Experimental results demonstrate that Sec- i MTOSA achieves an average of 93.7% accuracy in detecting NLDs while maintaining a secure RA process with only an average of 7.2% increase in end-to-end delay compared to non-secure traditional methods. These results validate the effectiveness of the model, demonstrating a high accuracy rate in identifying legitimate NLDs while maintaining a low computational overhead suitable for lightweight IoE-Edge environments. Although Sec- i MTOSA introduces minor end-to-end delays due to its embedded security features, it remains efficient for real-time IoE-Edge deployments. These findings establish CTI-driven RA as a scalable and secure approach for next-generation IoE-Edge networks.

Lightweight, privacy-aware and adversarial robust intrusion detection is required for the proliferation of Internet of Things (IoT) devices. In the Industrial Internet of Things (IIoT), centralized detectors can be compromised by adversarial perturbations via gradient-based attacks, making them susceptible to raw traffic. We suggest Federated Learning-Adaptive Gated Recurrent Unit (FL-AdGRU), a Federated approach that combines a lightweight Gated Recurrent Unit (GRU) classifier with alternating adversarial fine-tuning on each client using FGSM and PGD, without any communication overhead. A two-stage resampling scheme (UCAS-SMOTE) reduces the class-imbalance ratio from 4081:1 to ≈4:1, followed by 61 features being reduced to 40 by a mutual-information selector (MI-SelectK). Under this scenario, FL-AdGRU achieves 99.9% accuracy and 0.999 weighted F1 (+6.5 p.p. over the federated DNN baseline), with no loss of accuracy when facing clean attacks, and boosts Fast Gradient Sign Method FGSM/Projected Gradient Descent (PGD) robustness by +19.3/+19.0 p.p. at the same level of $ϵ$ = 0.1, thus effectively balancing the accuracy–robustness trade-off. It is robust (97.8%/84.2% on UNSW-NB15) and generalizes well to UNSW-NB15, while decaying slowly in skeptical scenarios (≈99.9% weighted F1 for moderate skew, 93.9%/86.7% for severe). Assuring data-locality privacy through exchange of only model weights; defenses against inference attack are left for future work. FL-AdGRU, with a total communication of 43.8 MB (≈50× less than centralized training), is deployable on bandwidth-constrained IIoT networks.