Objective. In order to increase the number of states classified by a brain–computer interface (BCI), we utilized motor imagery task where subjects imagined both force and speed hand clenching. Approach. The BCI simultaneously recorded electroencephalographic (EEG) functional near-infrared spectroscopy (fNIRS) signals. time-phase-frequency feature was extracted from EEG, whereas HbD [the difference oxy-hemoglobin (HbO) deoxy-hemoglobin (Hb)] used improve classification accuracy fNIRS. EEG...

Detecting vulnerabilities in source code using deep learning models is emerging as a valuable research area. The key issue to detect the accurate representation. Current approaches for detecting C/C++ programs use functions or lines of unit and only consider basic syntactic structure vulnerabilities. Unfortunately, still have vulnerability-unrelated information, which redundant vulnerability features not conducive learn patterns. This paper deeply analyzes essential attacks. Then, we propose...

With the continuous development of E-commerce, warehouse logistics is also facing emerging challenges, including more batches orders and shorter order processing cycles. When need to be processed simultaneously, some existing task scheduling methods may not able give a suitable plan, which delays reduces efficiency warehouse. Therefore, intelligent system that uses autonomous robots for automated storage becoming mainstream. Based on this concept, we propose multi-robot cooperative in The...

Code-reuse attack is a severe threat to computer systems as it can circumvent many existing security defenses and perform arbitrary behavior. Control-flow integrity (CFI) technique that restricts control-flow transfers prevent the attack. Although CFI has been implemented via various methods, including hardware-assisted extensions, current designs of fine-grained fail meet practical needs. The main hurdles include: 1) lack cost-effective design 2) insufficient they cannot enforce complete...

It is fundamentally challenging to build a secure system atop the current computer architecture. The complexity in software, hardware and ASIC manufacture has reached beyond capability of existing verification methodologies. Without whole-system verification, systems have no proven security. observed that are exposed variety attacks due existence large number exploitable security vulnerabilities. Some vulnerabilities difficult remove without significant performance impact because can be...

Memory corruption vulnerabilities are main causes of quite a few modern software attacks. Classical Data-flow integrity, which is originally implemented purely on soft-ware platforms, can perform good security effect against memory attacks, particularly the newly proposed data-oriented programming However, it introduces high space and time overheads. To tackle these limitations DFI, in this paper we present tagged supported data-flow TMDFI, hardware integrity implementation to enable...

Recent technological advances have accelerated the design and deployment of kinds secure applications on smartphones. Although users can access handle their data flexibly stably with mobile devices, not only computing it poses security challenges a new dimension that disclose lots sensitive privacy information over open devices networks as well. Thus, more malwares are emerging to compromise OS steal from these applications. In this paper, we propose payment framework TrustPAY TrustZone...

Control-hijacking attacks include code injection and reuse attacks. In recent years, with the emergence of defense mechanism data-execution prevention(DEP), have become mainstream, such as return-oriented programming(ROP), Jump-Oriented Programming(JOP), Counterfeit Object-oriented Programming(COOP). And a series defensive measures been proposed, DEP, address space layout randomization (ASLR), coarse-grained Control-Flow Integrity(CFI) fine-grained CFI. this paper, we propose new attack...

Continually disclosed vulnerabilities reveal that traditional computer architecture lacks the consideration of security. This article proposes a security-first architecture, with an Active Security Processor (ASP) integrated to conventional architectures. To reduce attack surface ASP and improve security whole system, is physically isolated from Computation Units (CPU) asymmetric address space, which enables both CPU run their operating system applications independently in own memory space....

Imbalanced issue becomes one of major bottleneck for further popularizing emotion recognition in actual applications. Recently, some resampling methods have been proposed to improve performance by balancing the training samples. However, over-sampling may lead overfitting, and undersampling would lose useful information. In this paper, we propose a multi-channel deep architecture both samples features imbalance. Specifically, design class correction loss function overcome gap between...

In this paper, we present a signal discretization and feature selection method to improve classification accuracy for fNIRS based brain computer interface (BCI) system, which can classifiy right hand clench force motor imagery speed at an of 69%-81% through 5 fold cross validation in 6 subjects. Difference between oxyhemoglobin deoxyhemoglobin (we abbreviate difference as HbD) is proposed new type shows outstanding performance some Linear kernal support vector machine (SVM) using four...

The current electronic-economy is booming, electronic-wallets, encrypted virtual-money, mobile payments, and other new generations of economic instruments are springing up. As the most important cornerstone, CPU facing serious security challenges. And with blowout actual application requirements, importance testing increasing. However, threats to computer systems also becoming increasingly rampant (now attackers often use multiple different types vulnerabilities construct complex attack...

Vulnerability detection is imperative to protect software systems from cyber attacks. However, existing methods either rely on experts directly define vulnerability patterns or features and then use machine learning generate automatically. It not only a laborious task but will miss many vulnerabilities incur high false-positive rate. Besides, large number of resources are required audit the precise location vulnerability. To solve problems, we propose AVDHRAM, systematic Automated Detection...

Return-Oriented Programming (ROP) is a typical attack technique that exploits return addresses to abuse existing code repeatedly. Most of the current address protecting mechanisms (also known as Backward-Edge Control-Flow Integrity) work only in limited threat models. For example, attacker cannot break memory isolation, or has no knowledge secret key random values. This paper presents novel, lightweight mechanism addresses, Zipper Stack, which authenticates all by chain structure using...

Memory corruption bugs in software written low-level languages like C or C++ are one of the oldest problems computer security. These unsafe vulnerable to errors relating misuse memory, such as buffer overflows, use-after-free. The exploit these vulnerabilities allows attackers tamper even take full control over program. In this paper, we propose a lightweight and comprehensive vulnerability detection approach for memory defects programs C++. is based on identification operations source code,...

Discovering the potential vulnerabilities in software plays a crucial role ensuring security of computer system. This paper proposes method that can assist auditors with analysis source code. When identify new vulnerabilities, our be adopted to make list recommendations may have same for auditors. Our relies on graph representation automatically extract mode PDG(program dependence graph, structure composed control and data dependence). Besides, it applied vulnerability extrapolation...

Secure logging as an indispensable part of any secure system in practice is well-understood by both academia and industry. However, providing security for audit logs on untrusted machine a large distributed still challenging task. The emergence wide availability log management tools prompted plenty work the community that allows clients or auditors to verify integrity data. Most recent solutions this problem focus space-efficiency public verifiability forward security. Unfortunately,...

The widespread deployment of unsafe programming languages such as C and C++, leaves many programs vulnerable to memory corruption attacks. With the continuous improvement control-flow hijacking defense methods, recent works on data-oriented attacks including Data-oriented Exploits (DOE), Programming (DOP), Block-oriented (BOP) have been showed that these can cause significant threat even in presence mechanism. Moreover, DFI (Date Flow Integrity) is a software-only approach for mitigating...

Vulnerability detection is an important means to protect computer software systems from network attacks and ensure data security. Automatic vulnerability by machine learning has become a research hotspot in recent years. The emergence of deep technology reduces human experts' boring arduous work defining features, which obtains advanced features that experts can not define intuitively. Among many neural networks, Recurrent Neural Network(RNN) structurally more suitable for processing...

With the rapid development of network technology and increasingly complexity system function, embedded is facing more serious threats. Previous researches on kernel monitoring protection widely relies higher privileged components, such as hardware virtualization extensions, to isolate security tools from potential attacks. These approaches increase both maintenance effort code base size which consequently increases risk having vulnerabilities. In this paper, we have proposed a mechanism...