IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency
This work addresses security vulnerabilities in AI systems for applications like autonomous vehicles and facial recognition, though it is incremental as it builds on existing backdoor detection research.
The paper tackles the problem of backdoor attacks in deep neural networks by proposing IBD-PSC, an input-level detection method that filters malicious images based on parameter-oriented scaling consistency, achieving effective detection with high accuracy and efficiency in experiments.
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can maliciously trigger model misclassifications by implanting a hidden backdoor during model training. This paper proposes a simple yet effective input-level backdoor detection (dubbed IBD-PSC) as a `firewall' to filter out malicious testing images. Our method is motivated by an intriguing phenomenon, i.e., parameter-oriented scaling consistency (PSC), where the prediction confidences of poisoned samples are significantly more consistent than those of benign ones when amplifying model parameters. In particular, we provide theoretical analysis to safeguard the foundations of the PSC phenomenon. We also design an adaptive method to select BN layers to scale up for effective detection. Extensive experiments are conducted on benchmark datasets, verifying the effectiveness and efficiency of our IBD-PSC method and its resistance to adaptive attacks. Codes are available at \href{https://github.com/THUYimingLi/BackdoorBox}{BackdoorBox}.