Solution by: Xinova Innovator, Ezekiel Kruglick, PhD
In this solution, a RAT detection analysis for recurring outlier network connections is proposed. In more detail, this describes a solution that can detect repeated “unusual” connections, when any single machine making unusual numbers of outliers is either compromised or has a user performing something deemed unusual.
Solution by: Xinova Innovator, Dr. Zhen Xiao
Action classification and deviation detection of network devices is proposed for this solution.
This describes a solution that performs traffic analysis and detects device anomalies. IoT devices generally have fixed activity patterns, however, personal devices tend to have diverse actions. By monitoring such patterns, and creating better accuracy of device classification, it is possible to more quickly neutralize an attack due to stricter detection criteria for a variety of devices.
Solution by: Xinova Innovators, Dr. Jun Fang and Dr. Xiaodong Wong
In this solution, what is proposed is a method of predicting network events by sending traceable particles and analyzing the flow of such data. This describes how a sensitive file can be broken into fragments that are distributed throughout a network system, and where the fragments are “moved” continuously within the system in a random manner. Unauthorized access to these fragments may actively verify a security situation.
Solution by: Xinova Innovator, Ezekiel Kruglick, PhD
In this paper, what is proposed is a security method of monitoring networking and computing devices. It describes a way of monitoring these devices by comparing the calculated versus the observed power signatures.
Solution by: Xinova Innovators, Xiaoqi Chen and Dr. Zhen Xiao
In this solution, a unique method of distinguishing real users from bots is proposed. In more detail, this describes an authentication system and method to authenticate human users by the user electing to assist in solving an NP-hard calculation problem that is too costly for bots to perform.
Solution by: Xinova Innovators, Shmuel Ur, Itzhak Pomerantz, and Vlad Dabija
This solution describes a method to detect the separation of individuals from their entry badges.
In more detail, this describes how a system can maintain awareness of spectator credentials and issue an alert when an attendee is without a badge, or a badge is without an attendee.
Solution by: Xinova Innovator, Natalya Segal
In this solution, a powerful tool that allows for efficient operations on large sets of dynamic surveillance information is proposed. In more detail, this describes the implementation of a scripting language that can facilitate responses and reduce times for actionable security challenges.
Solution by: Xinova Innovators, Jin Sam Kwak and Ju Hyung Son
This solution describes an efficient method of communication between control room and field agent using unique feature extraction. In more detail, this discloses how to select certain context-dependent features to facilitate describing suspects in a crowd.
Solution by: Xinova Innovator, Kevin Williams
This solution describes a method of collecting and communicating directly with spectators at an event location. In more detail, this describes how to make spectator contact information immediately accessible to security control center personnel, and have it available should agents require direct access for questioning and verification purposes.
Solution by: Xinova Innovators, Shmuel Ur
This solution describes a method for distinguishing people who are being evasive. In more detail, this describes how to utilize computers to recognize in people in both human-like and machine-like ways, and compare for discrepancies.
Solution by: Xinova Innovator, Noam Hadas
In this solution, a method to monitor physiological reactions is proposed. In more detail, this describes a new concept to the software/operator system by which data collected from operators is used as part of the analysis and presentation algorithms, in order to improve response.
Solution by: Xinova Innovators, Mordehai Margalit, Dani Zeevi, and Vlad Dabija
This solution describes a method for quickly assessing crowd sentiment. In more detail, this describes how to highlight important anomalies in images presented of crowds, and identify people that display different emotions than those around them in a way that reduces operational overload.
Solution by: Xinova Innovators, Shmuel Ur and Or Zilberman
This solution describes a method of using eye-tracking technology to monitor and manage video feeds from security cameras. In more detail, this describes how video feeds can be managed based on the security personnel’s behavior towards the delivered feeds.
Solution by: Xinova Innovators, Yang-Won Jung
In this solution, a method to select/recruit attendees who will participate in the surveillance is proposed. In more detail, a surveillance camera emits RF signal in direction of its field of view. The other camera determines whether it is in the Line of Sight (LoS) of the surveillance camera or not. Also, the other camera determines its facing direction in relation to the facing direction of the surveillance camera. Based on the determination, cameras which will become new surveillance cameras are decided.
Solution by: Xinova Innovator, David W. Ash
In this solution, the approach described is a method to help protect the next tier of celebrities—those requiring significantly more protection than the average person but not receiving government sponsored security. In more detail, a record is made of which fans are appearing at both the celebrity’s private and public events. An algorithm is provided for determining when particular people are appearing in the vicinity of these events to a degree greater than would be expected just via statistical noise.
Solution by: Xinova Innovator, Shmuel Ur
In this solution, a method to correlate a person to his phone number is proposed. In more detail, this teaches how to tie, using video surveillance, a phone number X to a person Y tracked in an event, using many-to-one matching between people and phones, and filtering down until there is a one-to-one match.
Solution by: Xinova Innovator, Xudong Ma
In this solution, a new object tracking algorithm using multiple cameras for surveillance applications is proposed. The proposed system can detect sudden-appearance-changes and occlusions using a hidden Markovian statistical model. The experimental results confirm that our system detect the sudden-appearance changes and occlusions reliably.
311 ½ Occidental Ave S
Seattle, WA 98104
+1 (206) 800-2678
Xinova Japan GK
Yaesu Mitsui Building 6F
2-7-2 Yaesu, Chuo-ku
Tokyo 104-0028 Japan
Xinova Innovation (Beijing) Consultancy Co. Ltd.
Room 2494, Level 24, Tower 3
China Central Place
77 Jianguo Road
Beijing, 100025 China
Xinova Asia Pte Ltd.
331 North Bridge Road
#22-01, Odeon Towers
+65 6408 5080
10th floor, Golfzone Tower
Seoul 06072, Korea
+82 2 6952 8840
Xinova Australasia Pty Ltd.
223 Liverpool St
Darlinghurst, NSW 2010
+61 2 8093 4850
Suite No 208, 2nd Floor
Survey No 414
Govinda Reddy (GR) Layout
Karnataka, 560076, India
Erottajankatu 5 A 4
Affiliate offices in Tel Aviv & Vienna