Despite the success of Convolutional Neural Networks (CNNs) in computer vision, it can be beneficial to reduce parameters, increase computational efficiency, and regulate overfitting. One such reduction technique is the use of so-called pooling, which gradually reduces the spatial dimensions of the data throughout the network. Recently, Quadtree-based Genetic Programming has achieved state-of-the-art results for optimizing spatial areas on customized requirements in different grid structures. Motivated by its success, we propose to extend this approach to pooling layers of CNNs. In this direction, this paper introduces a new way to look at each pooling layer. Specifically, we propose an Evolutionary Quadtree Pooling (EQP) method that can identify the best pooling scheme. By embedding multiple quadtrees set as a pooling scheme in the pooling layers of a CNN, we are able to operate crossover and mutation on the feature maps. The evolutionary process of EQP guides the search to provide more reliable evaluations, where each individual can be seen as a CNN with a new type of pooling scheme. Our experimental results show that the best candidate network of EQP outperforms state-of-the-art max, average, stochastic, median, soft, and mixed pooling in accuracy and overfitting reduction while maintaining low computational costs. Our codes are available at https://github.com/poweiharn/EQP.git.

Graph Neural Networks (GNNs) have shown promising performance in many applications, yet remain extremely difficult to train over large-scale graph datasets. Existing weight pruning techniques can prune out the layer weights; however, they cannot fully address the high computation complexity of GNN inference, caused by large graph size and complicated node connections. In this paper, we propose an Iterative Gradient Rank Pruning (IGRP) algorithm to find graph lottery tickets (GLT) of GNNs where each GLT includes a pruned adjacency matrix and a sub-network. Our IGRP can avoid layer collapse and the winning ticket achieves Maximal critical compression. We evaluate the proposed method on small-scale (Cora and Citeseer), medium-scale (PubMed and Wiki-CS), and large-scale (Ogbn-ArXiv and Ogbn-Products) graph datasets. We demonstrate that both Single-shot and Multi-shot of IGRP outperform the state-of-the-art unified GNN sparsification (UGS) framework on node classification. The source code can be found in https://github.com/poweiharn/IGRP_GNN.

The location-based alert system plays a primary factor on determining who is at risk during an emergency, such as a war zone in Ukraine. While users are willing to reveal their locations in exchange for timely alert in those situations, there is no guarantee that their private information does not fall into the wrong hands. For example, a soldier may be killed if his movement pattern is known by the enemy. One resolution to this issue is to encrypt the location information by trusted authority public key before it is transmitted. This approach provides location privacy and allows decryption only when the recipient’s location satisfies a certain predicate. However, the encryption itself may still be compromised if the location encoding is leaked. In this paper, we propose a Hilbert Curve Encoding which encrypts the user’s message along with her locations for private processing with the trusted authority. We further propose a hybrid HNGM−NEncoding which combines the Hilbert Curve Encoding and Gray Encoding. HNGM−Nhas the proprieties of a Hilbert Curve Encoding in its identifier and a Hamming distance of 1 between neighboring cells in a subgrid. As a consequence, the proposed HNGM−Nis less likely to leak neighboring cell identifier than Gray Encoding under random guessing attacks. Extensive experiment results show that our encoding methods are better than Hierarchical Encoding and comparable to Gray Encoding in terms of user response time, token remaining percentage, and execution time.

An RFID system is a contactless automatic identification technology and a solution to many business and personal applications. However, the privacy threats to RFID systems cause significant concerns in real RFID applications. Among the privacy issues in RFID systems, we are particularly interested in designing an RFID authentication protocol that achieves strong indistinguishability-based privacy (ind-privacy) and possesses the zero-knowledge property for active tags. In this article, a zero-knowledge authentication protocol (ZKAP) using quadratic residues is proposed. Then, an indistinguishability-based experiment using random oracles is modeled to prove that the proposed scheme achieves strong ind-privacy against active eavesdroppers. The zero-knowledge property is defined with respect to the tags’ private information against dishonest readers, and that property of our ZKAP is proven by constructing a polynomial time simulator that generates a transcript with the same distribution as that of ZKAP. Finally, the proposed protocol is implemented in a Raspberry Pi and a PC, and the performance is evaluated in terms of authentication time. The experimental results demonstrate that our ZKAP achieves its design goals.

A variety of optimal location problems have been extensively studied in the literature. However, limited visualization systems have been developed for illustrating optimal location selection process. In this demonstration, we present a system that visualizes an advanced solution that can efficiently answer multi-criteria optimal location updating query by incrementally updating the Minimum Overlapping Voronoi Diagram (MOVD) model. Not only does our system display an example as a practical multi-criteria optimal location updating query, but also visualizes the process of the query evaluation in a more intuitive manner. With the object insertion and deletion operations defined over the MOVD model, any object changes in an MOVD can be represented by removing the objects from initial datasets and adding them back with updated attributes. Moreover, Haxe toolkit is used to provide friendly and flexible user interfaces in our system.