Since the introduction of Security Operations Centers (SOCs) around 15 years ago, their importance has grown significantly, especially over the last five years. This is mainly due to the paramount necessity to prevent major cyber incidents and the resulting adoption of centralized security operations in businesses. Despite their popularity, existing academic work on the topic lacks a generally accepted view and focuses mainly on fragments rather than looking at it holistically. These shortcomings impede further innovation. In this paper, a comprehensive literature survey is conducted to collate different views. The discovered literature is then used to determine the current state-of-the-art of SOCs and derive primary building blocks. Current challenges within a SOC are identified and summarized. A notable shortcoming of academic research is its focus on the human and technological aspects of a SOC while neglecting the connection of these two areas by specific processes (especially by non-technical processes). However, this area is essential for leveraging the full potential of a SOC in the future.

/pdf/security-operations-center-a-systematic-study-and-open-4tgeqhxckq.pdf

Security Operations Center: A Systematic Study and Open Challenges

Pedestrian detection, despite the recent advances, still is of a great challenge to computer vision in wide range of diversified applications such as urban autonomous driving and intelligent transportation. Deep convolutional neural network has greatly contributed to the recent advances in pedestrian detection algorithms. The aim of this paper is to use modified single-shot detector (SSD) approach in pedestrian detection and then improve it by a novel deep architecture. The proposed deep architecture extracts initial Region of Interests (RoIs) using SSD approach, while it employs nine parallel fast RCNNs based on inception modules to estimate nine different parts of body. The proposed method takes the advantage of a secure border in each initial RoI to both create an Extended Region of Candidate Pedestrian (ERCP) and also to extract multi-RoIs. It then selects a number of RoIs within the ERCP as detected pedestrians which satisfy few reasonable criteria. We also propose a new training approach based on different body parts estimation which searches the best RoIs. Comprehensive experimental results demonstrate that the proposed method, deep model based on parts in pedestrian proposals, is a highly effective method that achieves very competitive performance on two most popular pedestrian detection datasets: Caltech-USA and INRIA. We have improved the log-average miss rate on the Caltech-USA and INRIA pedestrian datasets to 7.28% and 4.96%, respectively.

High-performance and deep pedestrian detection based on estimation of different parts

Blind Spot Monitoring in Light Vehicles — System Performance

Prediction of stopping distance for autonomous emergency braking using stereo camera pedestrian detection

Sensors are the quintessential part of Blind Spot Detection (BSD) systems, which have a profound effect on the performance of the system. Every sensor has its unique deficiencies that can deteriorate the performance of the system under grievous circumstances. Hence, making vital tasks in BSD such as object detection arduous. Indeed, previous studies have demonstrated that data fusion techniques can diminish the adverse effects of sensors and improve detection accuracy in the BSD system. One of the main advantages of data fusion is to improve detection accuracy and reduce the processing time by multiple sensors cooperation. We propose a BSD model that objects are detected in consecutive time intervals in the BSD system. Then, association techniques are employed for multi-sensor fusion since all sensors data are not ordinarily ready for fusion simultaneously. It should be noted that the orthodox approach in data association techniques in BSD often includes a global nearest neighbor, joint probabilistic data association, and multiple hypothesis tests. We simulate and compare these techniques by tracking multiple targets and multi-sensor fusion using virtual data in MATLAB. Furthermore, we illustrate that our multi-sensor fusion detection accuracy in the BSD system is augmented compared to a single sensor BSD system.

Blind Spot Detection System in Vehicles Using Fusion of Radar Detections and Camera Verification

Pedestrian detection is an important topic in different areas in particular Advance Driver Assistant Systems (ADAS) and Autonomous vehicles (AVs). Because of some intrinsic problems like intensity and light variation and different people’s clothing pedestrian detection is a challenging subject. In autonomous driving to avoid collisions a robust and reliable detection algorithm is essential. In recent years, vision becomes an effective part in autonomous driving that could provide a comprehensive cognition from surrounding that widely used in modern vehicles in different quantity and installation position. Image quality, faster detection algorithm with an optimum detection rate and providing more data for decision level are other challenges in this area. By using two cameras as a stereo vision system and extracting depth map and finding objects in Area of interest we get a stack of ROIs (region of interest) then by enhancing Image in selected ROIs by HIS image fusion technique better image quality for the detection level achieves.

Pedestrian Detection Using Image Fusion and Stereo Vision in Autonomous Vehicles

Connected and Autonomous Vehicles (CAVs) will play a crucial role in nextgeneration and intelligence cars. Autonomous Vehicles (AV) are equipped with the advanced RF and wireless communication and sensor infrastructure for supporting vehicular network. AVs not only help to empower aging populations, but also they provide a powerful, noninvasive, non-threatening modality by which to monitor, interact with, and respond to their passengers’ state of being. Ten million AVs or self-driving cars will be on the road by 2020, according to an indepth report recently. Proponents of AVs say that the technology has the potential to benefit society in a range of ways, from boosting economic productivity to reducing urban congestion. However, others including some potential consumers and corporate risk managers have expressed serious concerns over the cybersecurity of the so-called fleet of the future. In this research, we will describe how to develop and implement such functionalities highly secure, trust, reliable and accurate sensors. RF sensors like radars and multitude of other types of RF sensors arrays (IoT based) are an instrumental part of the general sensor configuration required for implementing a robust cyber-security strategy and enhancing privacy in addition to the other autonomous features. There are some challenges and threats such as:•What is a new and important threat in AV and what is the difference between it and the other threat occurred in cyber space?•How can AV be attacked?•What is the difference between security and privacy mechanisms for AV?•Could the risk management be ridable to define, control, and mitigate the risk in an AV?•Could cyber-criminals remotely hijack an autonomous car’s electronics with the intention of causing a crash?•Could terrorists command the vehicles similar to the weapons?•Could data stored on-board be unlocked?•Could the AV privacy and passengers be considered?•Is there any secure channel in V2V connection for AV?

Cyber Security Challenges in Autonomous Vehicle: Their Impact on RF Sensor and Wireless Technologies

Sensor selection is an essential aspect of blind spot detection (BSD) systems. Indeed, we must choose the sensors appropriately to accomplish high accuracy and performance in any driving condition. Each sensor has exclusive properties which are suitable for a few specific circumstances. Therefore, a comprehensive study is warranted to determine the optimum number of sensors and the type of sensors for BSD. Although sensors have some deficiencies which can deteriorate the whole system's performance, a combination of multiple types of sensors together with data fusion methods in most cases can substantially compensate for sensors imperfection. In this paper, we have concentrated on multi-sensor fusion in BSD system and its advantages which cannot be achieved in a single-sensor BSD system. A sensing structure for the BSD system is proposed considering the indispensable factors in BSD coupled with sensors constraints, features, and specifications.

Sensing Structure for Blind Spot Detection System in Vehicles

Information security management is a complicated task in cloud environment. Cloud service layers and multi-tenant architecture have created a complicated environment for developing and managing a monitoring and incident response environment in organizations. The main goal of this paper is to receive and analyze events from OpenStack environment. Events and system logs are received from OpenStack environment. The organization SOC must be customized to receive and detect cloud specific attacks. In this paper, we customize SOC for OpenStack environment to detect cloud specific attacks. The customized SOC receives and normalizes OpenStack alerts. We have developed new correlation rules and response scenarios for these alerts. We have presented evaluation results of customized SOC development in OpenStack. The customized SOC can detect OpenStack and hypervisor based attacks.

Hossein Gharaee Garakani

Papers

Pedestrian Detection Using Image Fusion and Stereo Vision in Autonomous Vehicles

Cyber Security Challenges in Autonomous Vehicle: Their Impact on RF Sensor and Wireless Technologies

Sensing Structure for Blind Spot Detection System in Vehicles

Blind Spot Detection System in Vehicles Using Fusion of Radar Detections and Camera Verification

Security operation center implementation on OpenStack