Resilience-Aware Fuzzy Optimization for Cyber Forensic Evidence Reconstruction under Adversarial Uncertainty

Cyber forensic analysis involves reconstructing event sequences from heterogeneous and often unreliable digital evidence. In adversarial environments, such evidence may be incomplete, noisy, or deliberately manipulated, making traditional deterministic and probabilistic approaches insufficient. This chapter proposes a resilience-aware fuzzy optimization framework for cyber forensic evidence reconstruction. The approach models evidence using fuzzy representations of confidence and uncertainty, and formulates reconstruction as a nonlinear optimization problem that integrates evidence support, uncertainty penalization, and inconsistency minimization. A novel inconsistency modeling mechanism is introduced to capture contradictions among evidence sources. To solve the resulting optimization problem, an adaptive hybrid metaheuristic combining Differential Evolution and Grey Wolf Optimization with fuzzy control is developed. The framework demonstrates improved robustness and consistency under adversarial perturbations, providing a reliable approach for cyber forensic reconstruction in uncertain environments.