LITE-RATE: LIghtweight TransformEr-Based Real-Time Defense Framework for Adversarial USB Keystroke Injection ATtack DEtection

Abstract

Universal serial bus (USB) human interface devices remain vulnerable to adversarial keystroke injection attacks because host systems implicitly trust connected peripherals. Recent poisoning and evasion attacks further reduce detection reliability by mimicking benign human typing patterns, creating overlapping benign and malicious USB traffic distributions. This article proposes LIghtweight TransformEr-Based Real-Time Defense Framework for Adversarial USB Keystroke Injection ATtack DEtection (LITE-RATE), a reliability-oriented lightweight transformer framework for real-time adversarial USB keystroke injection detection. LITE-RATE integrates kernel-level USB traffic acquisition, sliding-window feature representation, lightweight transformer models, layerwise pruning, few-shot adaptation, and dual-mode explainability to jointly address detection accuracy, latency, robustness, and transparency. Experimental results show that LITE-RATE achieves up to 92% detection accuracy with an average inference latency of 10.64 ms, demonstrating its suitability for real-time deployment on resource-constrained host systems.