Qingying Hao

Haoyu Zhai, Shuo Wang, Pirouz Naghavi et al.

Gaussian blur is widely used to blur human faces in sensitive photos before the photos are posted on the Internet. However, it is unclear to what extent the blurred faces can be restored and used to re-identify the person, especially under a high-blurring setting. In this paper, we explore this question by developing a deblurring method called Revelio. The key intuition is to leverage a generative model's memorization effect and approximate the inverse function of Gaussian blur for face restoration. Compared with existing methods, we design the deblurring process to be identity-preserving. It uses a conditional Diffusion model for preliminary face restoration and then uses an identity retrieval model to retrieve related images to further enhance fidelity. We evaluate Revelio with large public face image datasets and show that it can effectively restore blurred faces, especially under a high-blurring setting. It has a re-identification accuracy of 95.9%, outperforming existing solutions. The result suggests that Gaussian blur should not be used for face anonymization purposes. We also demonstrate the robustness of this method against mismatched Gaussian kernel sizes and functions, and test preliminary countermeasures and adaptive attacks to inspire future work.

Ya Xiao, Qingying Hao, Danfeng et al.

Many real-world cyber-physical systems (CPS) use proprietary cipher algorithms. In this work, we describe an easy-to-use black-box security evaluation approach to measure the strength of proprietary ciphers without having to know the algorithms. We quantify the strength of a cipher by measuring how difficult it is for a neural network to mimic the cipher algorithm. We define new metrics (e.g., cipher match rate, training data complexity and training time complexity) that are computed from neural networks to quantitatively represent the cipher strength. This measurement approach allows us to directly compare the security of ciphers. Our experimental demonstration utilizes fully connected neural networks with multiple parallel binary classifiers at the output layer. The results show that when compared with round-reduced DES, the security strength of Hitag2 (a popular stream cipher used in the keyless entry of modern cars) is weaker than 3-round DES.