Dual-filtering (DF) schemes for learning systems to prevent adversarial attacks
Abstract
Defenses against adversarial attacks are essential to ensure the reliability of machine-learning models as their applications are expanding in different domains. Existing ML defense techniques have several limitations in practical use. We proposed a trustworthy framework that employs an adaptive strategy to inspect both inputs and decisions. In particular, data streams are examined by a series of diverse filters before sending to the learning system and then crossed checked its output through anomaly (outlier) detectors before making the final decision. Experimental results (using benchmark data-sets) demonstrated that our dual-filtering strategy could mitigate adaptive or advanced adversarial manipulations for wide-range of ML attacks with higher accuracy. Moreover, the output decision boundary inspection with a classification technique automatically affirms the reliability and increases the trustworthiness of any ML-based decision support system. Unlike other defense techniques, our dual-filtering strategy does not require adversarial sample generation and updating the decision boundary for detection, makes the ML defense robust to adaptive attacks.
Publication Title
Complex and Intelligent Systems
Recommended Citation
Dasgupta, D., & Gupta, K. (2023). Dual-filtering (DF) schemes for learning systems to prevent adversarial attacks. Complex and Intelligent Systems, 9 (4), 3717-3738. https://doi.org/10.1007/s40747-022-00649-1
