Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection
A diagnostic-first methodology is proposed that localizes trigger-relevant features through constrained perturbation analysis and detects poisoning-induced behavioral drift by comparison with a distilled baseline model and enables targeted mitigation via automated data sanitization or neuron pruning.
Florian Spelter, J. Loevenich, Tobias Hürten et al.
· 0 citations