Abstract In Crypto’19, Gohr proposed the first deep learning-based key recovery attack on 11-round Speck32/64, which opens the direction of neural-aided cryptanalysis. Until now, neural-aided cryptanalysis still faces two problems: (i) the attack complexity estimations rely purely on practical experiments; (ii) it does not work when there are not enough neutral bits. To the best of our knowledge, we are the first to solve these two problems. In this paper, we propose a Neural-Aided Statistical Attack (NASA) that has the following advantages: (i) NASA supports estimating the theoretical complexity. (ii) NASA does not rely on any special properties including neutral bits. Moreover, we propose three methods for reducing the complexity of NASA. One of the methods, which is based on a newly proposed concept named Informative Bit that reveals an important phenomenon, makes NASA applicable to large-size ciphers. We have performed a series of experiments on round reduced Speck32/64, DES, and Speck96/96. These experiments do not only verify the correctness of NASA, but also further highlight the advantage and potential of NASA. Our work arguably raises a new direction for neural-aided cryptanalysis.

Abstract Neural-aided cryptanalysis is a challenging topic, in which the neural distinguisher ($\mathcal{ND}$) is a core module. In this paper, we propose a new $\mathcal{ND}$ considering multiple ciphertext pairs simultaneously. Besides, multiple ciphertext pairs are constructed from different keys. The motivation is that the distinguishing accuracy can be improved by exploiting features derived from multiple ciphertext pairs. To verify this motivation, we have applied this new $\mathcal{ND}$ to five different ciphers. Experiments show that taking multiple ciphertext pairs as input indeed brings accuracy improvement. Then, we prove that our new $\mathcal{ND}$ applies to two different neural-aided key recovery attacks. Moreover, the accuracy improvement is helpful for reducing the data complexity of the neural-aided statistic attack. The code is available at https://github.com/AI-Lab-Y/ND_mc.

By modeling an action as the evolution of postures, Posture-based recognition algorithms possess interpretative patterns. However, there are two limitations resulted from individual diversity. First, the same action can be performed by different organs. Such actions are denoted as ambiguous actions. Second, the postures of the same action can be badly influenced by personal characteristics (e.g., personal habits and the height). In order to tackle the problems above, we propose a hierarchical posture representation (HPR). A posture is composed of several skeletal points. Each skeletal point can perform a unique operation and provide a certain amount of information. Thus, an action can be recognized based on the relationships and the information contribution levels of all skeletal points. In HPR, each skeletal point is first represented by its interaction features with other skeletal points. The interaction features are independent of the type of posture. Then, the information contribution level of each skeletal point is estimated based on its interaction features. An end-to-end adaptive action recognition network (AARN) is proposed to accomplish the three processes (estimating the information contribution level, mining the relationships among skeletal points, and recognizing actions). The proposed algorithm shows promising accuracy on two databases. Our work does not only solve the problem above but also introduce a novel action modeling method.

Human activity recognition (HAR) is widely applied to many industrial applications. In the context of Industry 4.0, driven by the same demand of machines' self-organizing ability, HAR can also be adopted in elderly healthcare. However, HAR should be adaptive to the application scenarios in elderly healthcare. In this paper, we propose a nonintrusive activity recognition method that can be applied to long-term and unobtrusive monitoring for elderlies. The method is robust to obstruction and nontarget object interference. Skeleton sequence is estimated from RGB images. Based on two activity continuity metrics, an interframe matching algorithm is proposed to filter nontarget objects. In order to make full use of spatial-temporal information, we propose a novel activity encoding method based on the interframe joints distances. A convolutional neural network is used to learn the distinguishing features automatically. A specific data augmentation method is designed to avoid the overfitting problem on small-scale datasets. The experiments are performed on two public activity datasets and a newly released noisy activity dataset (NAD). The NAD contains obstruction, nontarget object interference. The experimental results show that the proposed method achieves the state-of-the-art performance while only using one ordinary camera. The proposed method is robust to a realistic environment.

Color guided depth up-sampling always suffers from texture copy artifacts and depth discontinuities blurring. This phenomenon is due to the depth discontinuity and color image edges at the corresponding location are not always consistent. In this paper, based on the analysis of the above two problems, we proposed an improved Markov Random Filed (MRF) model, which can reduce negative influence from pixels at the inconsistent location more effectively. Furthermore, the improved MRF model can also reduce the negative influence of noises from depth map. To determine pixels of inconsistent regions, a new concept of pixel confidence is proposed. Pixel confidence indicates the probability that pixel is at the inconsistent regions, which is embedded into the improved MRF model. The proposed method is tested on both the simulated and real datasets. The proposed method can better suppress texture copy artifact and preserve sharp depth discontinuities. Experimental results show that the proposed method also has lower mean absolutely error(MAE) than other methods in most cases.