WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
This addresses the need for stealthier and more effective backdoor attacks in AI security, representing an incremental improvement over existing methods.
The paper tackles the problem of low fidelity and detectability in backdoor attacks on deep neural networks by proposing WaveAttack, a frequency-based method using Discrete Wavelet Transform and asymmetric obfuscation, resulting in up to 28.27% improvement in PSNR, 1.61% in SSIM, and 70.59% reduction in IS compared to state-of-the-art methods.
Due to the popularity of Artificial Intelligence (AI) technology, numerous backdoor attacks are designed by adversaries to mislead deep neural network predictions by manipulating training samples and training processes. Although backdoor attacks are effective in various real scenarios, they still suffer from the problems of both low fidelity of poisoned samples and non-negligible transfer in latent space, which make them easily detectable by existing backdoor detection algorithms. To overcome the weakness, this paper proposes a novel frequency-based backdoor attack method named WaveAttack, which obtains image high-frequency features through Discrete Wavelet Transform (DWT) to generate backdoor triggers. Furthermore, we introduce an asymmetric frequency obfuscation method, which can add an adaptive residual in the training and inference stage to improve the impact of triggers and further enhance the effectiveness of WaveAttack. Comprehensive experimental results show that WaveAttack not only achieves higher stealthiness and effectiveness, but also outperforms state-of-the-art (SOTA) backdoor attack methods in the fidelity of images by up to 28.27\% improvement in PSNR, 1.61\% improvement in SSIM, and 70.59\% reduction in IS.