With the development of the Internet, malicious code attacks have increased exponentially, with malicious code variants ranking as a key threat to Internet security. The ability to detect variants of malicious code is critical for protection against security breaches, data theft, and other dangers. Current methods for recognizing malicious code have demonstrated poor detection accuracy and low detection speeds. This paper proposed a novel method that used deep learning to improve the detection of malware variants. In prior research, deep learning demonstrated excellent performance in image recognition. To implement our proposed detection method, we converted the malicious code into grayscale images. Then, the images were identified and classified using a convolutional neural network (CNN) that could extract the features of the malware images automatically. In addition, we utilized a bat algorithm to address the data imbalance among different malware families. To test our approach, we conducted a series of experiments on malware image data from Vision Research Lab. The experimental results demonstrated that our model achieved good accuracy and speed as compared with other malware detection models.

Detection of Malicious Code Variants Based on Deep Learning

/pdf/shu-ping-computational-homology-1o0kbmii0p.pdf

書評 Computational Homology

s for articles or notes should entice the prospective reader into exploring the subject of the paper and should make it clear to the reader why this paper is interesting and important. The abstract should highlight the concepts of the paper rather than summarize the mechanics. The abstract is the first impression of the paper, not a technical summary of the paper. Excessive use of notation is discouraged as it can limit the interest of the broad readership of the MAA and can limit searchability of the article. Letters to the editor on any topic are invited. Comments, criticisms, and suggestions for making the Monthly more lively, entertaining, and informative can be forwarded to editor Susan Colley. Formatting and templates Authors who use LaTeX are urged to use the Monthly template and maa-monthly.sty (and its standard environments) with no custom formatting. Journal names in references should match those used on MathSciNet. For filler, please download and use the following Monthly filler template. References References should be presented in a separate section at the end of the document. The references should be listed alphabetically by the first author’s last name, then, as needed, by the co-author’s last names and the resource’s

/pdf/american-mathematical-monthly-375wbk2yzc.pdf

American Mathematical Monthly

From the Publisher:
This mathematically oriented introduction to the theory of logic programming presents a systematic exposition of the resolution method for propositional, first-order, and Horn- clause logics, together with an analysis of the semantic aspects of the method. It is through the inference rule of resolution that both proofs and computations can be manipulated on computers, and this book contains elegant versions and proofs of the fundamental theorems and lemmas in the proof theory of logic programming. Advanced topics such as recursive complexity and negation as failure and its semantics are covered, and streamlined setups for SLD- and SLDNF-resolution are described.
No other book treats this material in such detail and with such sophistication. Doets provides a novel approach to resolution that is applied to the first-order case and the case of (positive) logic programs. In contrast to the usual approach, the concept of a resolvent is defined nonconstructively, without recourse to the concept of unification, allowing the soundness and completeness proofs to be carried out in a more economic way. Other new material includes computability results dealing with analytical hierarchy, results on infinite derivations and an exposition on general logic programs using 3-valued logic.

From Logic to Logic Programming

In a biological nervous system, astrocytes play an important role in the functioning and interaction of neurons, and astrocytes have excitatory and inhibitory influence on synapses. In this work, with this biological inspiration, a class of computation devices that consist of neurons and astrocytes is introduced, called spiking neural P systems with astrocytes (SNPA systems). The computation power of SNPA systems is investigated. It is proved that SNPA systems with simple neurons (all neurons have the same rule, one per neuron, of a very simple form) are Turing universal in both generative and accepting modes. If a bound is given on the number of spikes present in any neuron along a computation, then the computation power of SNPA systems is diminished. In this case, a characterization of semilinear sets of numbers is obtained.

Spiking neural p systems with astrocytes

A parallel algorithm for skeletonizing images by using spiking neural P systems

A uniform family of tissue P systems with cell division solving 3-COL in a linear time

A new programming language for membrane computing, P-Lingua, is developed in this paper. This language is not designed for a specific simulator software. On the contrary, its purpose is to offer a general syntactic framework that could define a unified standard for membrane computing, covering a broad variety of models. At the present stage, P-Lingua can only handle P systems with active membranes, although the authors intend to extend it to other models in the near future.

P-Lingua allows to write programs in a friendly way, as its syntax is very close to standard scientific notation, and parameterized expressions can be used as shorthand for sets of rules. There is a built-in compiler that parses these human-style programs and generates XML documents that can be given as input to simulation tools, while different plugins can be designed to produce specific adequate outputs for existing simulators.

Furthermore, we present in this paper an integrated development environment that plays the role of an interface where P-Lingua programs can be written and compiled. We also present a simulator for the class of recognizer P systems with active membranes, and we illustrate it by following the writing, compiling and simulating processes with a family of P systems solving the SAT problem.

/pdf/a-p-lingua-programming-environment-for-membrane-computing-j0qwvvad1b.pdf

A P-Lingua Programming Environment for Membrane Computing

Membrane computing is a well-known research area in computer science inspired by the organization and behavior of live cells and tissues. Their computational devices, called P systems, work in parallel and distributed mode and the information is encoded by multisets in a localized manner. All these features make P systems appropriate for dealing with digital images. In this paper, some of the open research lines in the area are presented, focusing on segmentation problems, skeletonization and algebraic-topological aspects of the images. An extensive bibliography about the application of membrane computing to the study of digital images is also provided.

Daniel Díaz-Pernil

Papers

A parallel algorithm for skeletonizing images by using spiking neural P systems

A uniform family of tissue P systems with cell division solving 3-COL in a linear time

A P-Lingua Programming Environment for Membrane Computing

Membrane computing and image processing: a short survey

Segmenting images with gradient-based edge detection using Membrane Computing