Event-Driven Spiking Learning Algorithm Using Aggregated Labels.

Traditional spiking learning algorithm aims to train neurons to spike at a specific time or on a particular frequency, which requires precise time and frequency labels in the training process. While in reality, usually only aggregated labels of sequential patterns are provided. The aggregate-label (AL) learning is proposed to discover these predictive features in distracting background streams only by aggregated spikes. It has achieved much success recently, but it is still computationally intensive and has limited use in deep networks. To address these issues, we propose an event-driven spiking aggregate learning algorithm (SALA) in this article. Specifically, to reduce the computational complexity, we improve the conventional spike-threshold-surface (STS) calculation in AL learning by analytical calculating voltage peak values in spiking neurons. Then we derive the algorithm to multilayers by event-driven strategy using aggregated spikes. We conduct comprehensive experiments on various tasks including temporal clue recognition, segmented and continuous speech recognition, and neuromorphic image classification. The experimental results demonstrate that the new STS method improves the efficiency of AL learning significantly, and the proposed algorithm outperforms the conventional spiking algorithm in various temporal clue recognition tasks.

Susceptible user search for defending opinion manipulation.

The development of cyberspace offers unprecedentedly convenient access to online communication, thus inducing malicious individuals to subtly manipulate user opinions for benefits. Such malicious manipulations usually target those influential and susceptible users to mislead and control public opinion, posing a bunch of threats to public security. Therefore, an intelligent and efficient searching strategy for targeted users is one prominent and critical approach to defend malicious manipulations. However, the major body of current studies either provide solutions under ideal scenarios or offer inefficient solutions without guaranteed performance. As a result, this work adopts the combination of unsupervised learning and heuristic search to discover susceptible and key users for defense. We first propose a greedy algorithm fully considering the susceptibilities of different users, then adopt unsupervised learning and utilize the community property to design an accelerated algorithm. Moreover, the approximation guarantees of both greedy and community-based algorithms are systematically analyzed for some practical circumstances. Extensive experiments on real-world datasets demonstrate that our algorithms significantly outperform the state-of-the-art algorithm.

Inference Attacks and Controls on Genotypes and Phenotypes for Individual Genomic Data.

The rapid growth of DNA-sequencing technologies motivates more personalized and predictive genetic-oriented services, which further attract individuals to increasingly release their genome information to learn about personalized medicines, disease predispositions, genetic compatibilities, etc. Individual genome information is notoriously privacy-sensitive and highly associated with relatives. In this paper, we present an inference attack algorithm to predict target genotypes and phenotypes based on belief propagation in factor graphs. With this algorithm, an attacker can effectively predict the target genotypes and phenotypes of target individuals based on genome information shared by individuals or their relatives, and genotype and phenotype association from genome-wide association study (GWAS). To address the privacy threats resulted from such inference attacks, we elaborate the metrics to evaluate data utility and privacy and then present a data sanitization method. We evaluate our inference attack algorithm and data sanitization method on real GWAS dataset: Age-related macular degeneration (AMD) case/control dataset. The evaluation results show that our work can effectively defense against genome threats while guaranteeing data utility.

Online Sensor Drift Compensation for E-Nose Systems Using Domain Adaptation and Extreme Learning Machine.

Sensor drift is a common issue in E-Nose systems and various drift compensation methods have received fruitful results in recent years. Although the accuracy for recognizing diverse gases under drift conditions has been largely enhanced, few of these methods considered online processing scenarios. In this paper, we focus on building online drift compensation model by transforming two domain adaptation based methods into their online learning versions, which allow the recognition models to adapt to the changes of sensor responses in a time-efficient manner without losing the high accuracy. Experimental results using three different settings confirm that the proposed methods save large processing time when compared with their offline versions, and outperform other drift compensation methods in recognition accuracy.

Common and distinct changes of default mode and salience network in schizophrenia and major depression.

Brain imaging reveals schizophrenia as a disorder of macroscopic brain networks. In particular, default mode and salience network (DMN, SN) show highly consistent alterations in both interacting brain activity and underlying brain structure. However, the same networks are also altered in major depression. This overlap in network alterations induces the question whether DMN and SN changes are different across both disorders, potentially indicating distinct underlying pathophysiological mechanisms. To address this question, we acquired T1-weighted, diffusion-weighted, and resting-state functional MRI in patients with schizophrenia, patients with major depression, and healthy controls. We measured regional gray matter volume, inter-regional structural and intrinsic functional connectivity of DMN and SN, and compared these measures across groups by generalized Wilcoxon rank tests, while controlling for symptoms and medication. When comparing patients with controls, we found in each patient group SN volume loss, impaired DMN structural connectivity, and aberrant DMN and SN functional connectivity. When comparing patient groups, SN gray matter volume loss and DMN structural connectivity reduction did not differ between groups, but in schizophrenic patients, functional hyperconnectivity between DMN and SN was less in comparison to depressed patients. Results provide evidence for distinct functional hyperconnectivity between DMN and SN in schizophrenia and major depression, while structural changes in DMN and SN were similar. Distinct hyperconnectivity suggests different pathophysiological mechanism underlying aberrant DMN-SN interactions in schizophrenia and depression.

Many-Objective Particle Swarm Optimization Using Two-Stage Strategy and Parallel Cell Coordinate System.

It is a daunting challenge to balance the convergence and diversity of an approximate Pareto front in a many-objective optimization evolutionary algorithm. A novel algorithm, named many-objective particle swarm optimization with the two-stage strategy and parallel cell coordinate system (PCCS), is proposed in this paper to improve the comprehensive performance in terms of the convergence and diversity. In the proposed two-stage strategy, the convergence and diversity are separately emphasized at different stages by a single-objective optimizer and a many-objective optimizer, respectively. A PCCS is exploited to manage the diversity, such as maintaining a diverse archive, identifying the dominance resistant solutions, and selecting the diversified solutions. In addition, a leader group is used for selecting the global best solutions to balance the exploitation and exploration of a population. The experimental results illustrate that the proposed algorithm outperforms six chosen state-of-the-art designs in terms of the inverted generational distance and hypervolume over the DTLZ test suite.

A layered searchable encryption scheme with functional components independent of encryption methods.

Searchable encryption technique enables the users to securely store and search their documents over the remote semitrusted server, which is especially suitable for protecting sensitive data in the cloud. However, various settings (based on symmetric or asymmetric encryption) and functionalities (ranked keyword query, range query, phrase query, etc.) are often realized by different methods with different searchable structures that are generally not compatible with each other, which limits the scope of application and hinders the functional extensions. We prove that asymmetric searchable structure could be converted to symmetric structure, and functions could be modeled separately apart from the core searchable structure. Based on this observation, we propose a layered searchable encryption (LSE) scheme, which provides compatibility, flexibility, and security for various settings and functionalities. In this scheme, the outputs of the core searchable component based on either symmetric or asymmetric setting are converted to some uniform mappings, which are then transmitted to loosely coupled functional components to further filter the results. In such a way, all functional components could directly support both symmetric and asymmetric settings. Based on LSE, we propose two representative and novel constructions for ranked keyword query (previously only available in symmetric scheme) and range query (previously only available in asymmetric scheme).

Query-biased preview over outsourced and encrypted data.

For both convenience and security, more and more users encrypt their sensitive data before outsourcing it to a third party such as cloud storage service. However, searching for the desired documents becomes problematic since it is costly to download and decrypt each possibly needed document to check if it contains the desired content. An informative query-biased preview feature, as applied in modern search engine, could help the users to learn about the content without downloading the entire document. However, when the data are encrypted, securely extracting a keyword-in-context snippet from the data as a preview becomes a challenge. Based on private information retrieval protocol and the core concept of searchable encryption, we propose a single-server and two-round solution to securely obtain a query-biased snippet over the encrypted data from the server. We achieve this novel result by making a document (plaintext) previewable under any cryptosystem and constructing a secure index to support dynamic computation for a best matched snippet when queried by some keywords. For each document, the scheme has O(d) storage complexity and O(log(d/s) + s + d/s) communication complexity, where d is the document size and s is the snippet length.