The ubiquity of fake news has been a serious problem on the Internet. Recommender systems, in particular, contribute to this issue by creating echo chambers of misinformation. In light of these observations, we address the issue of fake news mitigation through the lens of recommender systems. This paper introduces a novel adaptation of the collaborative filtering algorithm that models untrustworthy online users in order to remove them from the candidate user’s neighborhood. The proposed approach, FAke News Aware Recommender system (FANAR), is an alteration of the collaborative filtering strategy that considerably prevents the propagation of fake news by avoiding untrustworthy neighbors. Furthermore, we create FNEWR, a dataset for the Fake News Recommendation system, to fulfill our goal. Our experiments reveal that FANAR surpasses the current leading news recommendation techniques in its ability to suggest personalized news and mitigate the spread of false information.
Organisations rely on warnings, notifications, microlearning, and simulated exercises to promote secure employee behaviour, yet repeated exposure can reduce responsiveness to a specific intervention, and sustained exposure across interventions can make further automated intervention undesirable. This paper proposes an exposure-aware self-adaptive architecture that separates three runtime decisions: whether an observed behavioural gap requires a response, whether accumulated cross-intervention burden still permits automation or calls for human review, and which eligible intervention is currently most suitable. Candidate selection combines intervention-specific responsiveness, which decreases with exposure and recovers over time, with employee-specific efficacy learned from observed outcomes, so that each decision is traceable to auditable runtime state. The architecture is evaluated through simulation; no organisational or employee data are used. A policy-independent synthetic generator (144 worlds, replicated on 144 independent worlds) compares it with nine baselines, including the Upper Confidence Bound (UCB) policy UCB1, Thompson sampling, discounted UCB, a Linear Upper Confidence Bound (LinUCB) contextual bandit, and round-robin rotation. Where repeated delivery attenuates the specific intervention, the architecture exceeds UCB1 by 0.049 and its own ablation by 0.073 on a synthetic outcome scale, but is level with LinUCB and at most marginally ahead of Thompson sampling (differences of at most 0.005) and slightly trails rotation; without exposure effects, exploitative selectors perform better. The contribution is therefore an auditable organisation of adaptation responsibilities, not a superior selection algorithm.
Attribute-Based Access Control (ABAC) evaluates authorization decisions per request, based on the current attribute context, and does not natively enforce control-flow order or history-based constraints such as Separation-of-Duty and Binding-of-Duty. As a result, ABAC-compliant request sequences may still violate the underlying business process. This paper introduces the Workflow Policy Agent (WPA), a decoupled workflow-aware extension of ABAC that composes request-level authorization with workflow-enabledness conditions to realize Just-in-Time access control over a single workflow, and extends it to concurrent, multi-instance, and hierarchical sub-workflow execution using Hierarchical Coloured Petri Nets.We formally prove three properties. The resulting unified policy is a conservative extension of ABAC. Every accepted execution trace is simultaneously ABAC-authorized and workflow-compliant. Under the stated well-formedness, progress, fairness, and finite-spawning assumptions, we prove WPA-soundness for workflows constructed from a selected subset of workflow patterns, including hierarchical composition. A prototype implementing the model as an infrastructure-agnostic, policy-as-code-compatible sidecar demonstrates feasibility on a loan-approval case study, including across hierarchical workflow boundaries. Using synthetic workloads up to 10^6 task templates and 10^5 concurrent cases, per-request latency overhead remains in the tens of milliseconds across the tested configurations.