Frontiers of Computer Science最新文献

Face attribute classification (FAC) is a high-profile problem in biometric verification and face retrieval. Although recent research has been devoted to extracting more delicate image attribute features and exploiting the inter-attribute correlations, significant challenges still remain. Wavelet scattering transform (WST) is a promising non-learned feature extractor. It has been shown to yield more discriminative representations and outperforms the learned representations in certain tasks. Applied to the image classification task, WST can enhance subtle image texture information and create local deformation stability. This paper designs a scattering-based hybrid block, to incorporate frequency-domain (WST) and image-domain features in a channel attention manner (Squeeze-and-Excitation, SE), termed WS-SE block. Compared with CNN, WS-SE achieves a more efficient FAC performance and compensates for the model sensitivity of the small-scale affine transform. In addition, to further exploit the relationships among the attribute labels, we propose a learning strategy from a causal view. The cause attributes defined using the causality-related information can be utilized to infer the effect attributes with a high confidence level. Ablative analysis experiments demonstrate the effectiveness of our model, and our hybrid model obtains state-of-the-art results in two public datasets.

Due to the advantages of high volume of transactions and low resource consumption, Directed Acyclic Graph (DAG)-based Distributed Ledger Technology (DLT) has been considered a possible next-generation alternative to block-chain. However, the security of the DAG-based system has yet to be comprehensively understood. Aiming at verifying and evaluating the security of DAG-based DLT, we develop a Multi-Agent based IOTA Simulation platform called MAIOTASim. In MAIOTASim, we model honest and malicious nodes and simulate the configurable network environment, including network topology and delay. The double-spending attack is a particular security issue related to DLT. We perform the security verification of the consensus algorithms under multiple double-spending attack strategies. Our simulations show that the consensus algorithms can resist the parasite chain attack and partially resist the splitting attack, but they are ineffective under the large weight attack. We take the cumulative weight difference of transactions as the evaluation criterion and analyze the effect of different consensus algorithms with parameters under each attack strategy. Besides, MAIOTASim enables users to perform large-scale simulations with multiple nodes and tens of thousands of transactions more efficiently than state-of-the-art ones.

The discourse analysis task, which focuses on understanding the semantics of long text spans, has received increasing attention in recent years. As a critical component of discourse analysis, discourse relation recognition aims to identify the rhetorical relations between adjacent discourse units (e.g., clauses, sentences, and sentence groups), called arguments, in a document. Previous works focused on capturing the semantic interactions between arguments to recognize their discourse relations, ignoring important textual information in the surrounding contexts. However, in many cases, more than capturing semantic interactions from the texts of the two arguments are needed to identify their rhetorical relations, requiring mining more contextual clues. In this paper, we propose a method to convert the RST-style discourse trees in the training set into dependency-based trees and train a contextual evidence selector on these transformed structures. In this way, the selector can learn the ability to automatically pick critical textual information from the context (i.e., as evidence) for arguments to assist in discriminating their relations. Then we encode the arguments concatenated with corresponding evidence to obtain the enhanced argument representations. Finally, we combine original and enhanced argument representations to recognize their relations. In addition, we introduce auxiliary tasks to guide the training of the evidence selector to strengthen its selection ability. The experimental results on the Chinese CDTB dataset show that our method outperforms several state-of-the-art baselines in both micro and macro F1 scores.

The information society depends increasingly on risk assessment and management systems as means to adequately protect its key information assets. The availability of these systems is now vital for the protection and evolution of companies. However, several factors have led to an increasing need for more accurate risk analysis approaches. These are: the speed at which technologies evolve, their global impact and the growing requirement for companies to collaborate. Risk analysis processes must consequently adapt to these new circumstances and new technological paradigms. The objective of this paper is, therefore, to present the results of an exhaustive analysis of the techniques and methods offered by the scientific community with the aim of identifying their main weaknesses and providing a new risk assessment and management process. This analysis was carried out using the systematic review protocol and found that these proposals do not fully meet these new needs. The paper also presents a summary of MARISMA, the risk analysis and management framework designed by our research group. The basis of our framework is the main existing risk standards and proposals, and it seeks to address the weaknesses found in these proposals. MARISMA is in a process of continuous improvement, as is being applied by customers in several European and American countries. It consists of a risk data management module, a methodology for its systematic application and a tool that automates the process.