By a News Reporter-Staff News Editor at Journal of Engineering -- THE BOEING COMPANY (Chicago, IL) has been issued patent number 9596259, according to news reporting originating out of Alexandria, Virginia, by VerticalNews editors.
The patent's inventors are Handel, Mark Jonathan (Seattle, WA); Stuart, Douglas Alan (St. Charles, MO); Taylor, Hugh L (Mukilteo, WA); Dorris, Steve A. (Saint Peters, MO); Wilson, Brett Michael (Seattle, WA).
This patent was filed on November 5, 2014 and was published online on March 14, 2017.
From the background information supplied by the inventors, news correspondents obtained the following quote: "Field of the Disclosure
"The embodiments described herein relate to a method and system of a Dendritic Cell Algorithm module using the Dendritic Cell Algorithm to detect malware in computer systems.
"Description of the Related Art
"Malware (viruses, trojans, 'advanced persistent threats,' etc.) represents a significant potential risk in embedded network systems, such as, for example, computer networks in factory control systems. Safeguarding the integrity of a given network is often an important task for ensuring the overall safety of critical systems. As a result, detection of viruses and malware is an increasingly critical task in embedded systems.
"Unfortunately, recent trends demonstrate that malware creators are willing to dedicate significant time and resources to the dissemination of malware, and the malware can often be cloaked and hidden in sophisticated ways. Further, continual development of malware requires users to continually take action to update additional malware protection in an effort to protect their devices and/or systems. Usefully, viruses and hosts have been waging an on-going war in the biological domain for many millennia. The outcome of the biological war has been a remarkably sophisticated and subtle system that can quickly detect, attack, and kill harmful invaders, while managing to avoid not only damage to the self, but also not killing other symbiotic organisms in the body.
"Artificial immune systems (AIS) are a collection of algorithms developed from models or abstractions of the function of the cells of the human immune system. One category of AIS is based on the Danger Theory, and includes the Dendritic Cell Algorithm (DCA), which is based on the behavior of Dendritic Cells (DCs) within the human immune system. DCs have the power to suppress or activate the immune system through the correlation of signals from an environment, combined with location markers in the form of antigen. The function of a DC is to instruct the immune system to act when the body is under attack, policing the tissue for potential sources of damage. DCs are natural anomaly detectors, they are the sentinel cells of the immune system. The DCA has demonstrated potential as a static classifier for a machine learning data set and anomaly detector for real-time port scan detection.
"The DCA has been described in a number of references, including Greensmith, Aickelin and Twycross, Articulation and Clarification of the Dendritic Cell Algorithm. In Proc. of the 5th International Conference on Artificial Immune Systems, LNCS 4163, 2006, pp. 404-417. The following features of the DCA differentiate the algorithm from other AIS algorithms: (1) multiple signals are combined and are a representation of environment or context information; (2) signals are combined with antigen in a temporal and distributed manner; (3) pattern matching is not used to perform detection, unlike negative selection; and (4) cells of the innate immune system are used as inspiration, not the adaptive immune cells, and unlike clonal selection, no dynamic learning is attempted.
"As described in the DCA literature, DCs can perform various functions, depending on their state of maturation. Modulation between these maturation states is facilitated by the detection of signals within the tissue, namely: (1) danger signals, (2) pathogenic associated molecular patterns (PAMPs), (3) apoptotic signals (safe signals), and (4) inflammatory cytokines. The DCA has been implemented successfully in various localized applications, which have made use of danger signals, PAMPs, and safe signals. Existing DCA implementations have used only a single signal vector as an indication of the state of the environment. The single signal vector is made up of a vector of four floating point values, representing PAMP, danger, safe and inflammation.
"In an actual implementation of the DCA it may be necessary to have multiple indicators, each of which describes one feature of the environment. For instance, in an embedded network, indicators that indicate the status of various aspects, such as overall bandwidth utilization, recent network traffic endpoints, and time since last heartbeat event, may all contribute to the state of the environment. The DCA's performance, with respect to true and false positives, is often improved by adding additional indicators to be considered by the DCA. This mimics the behavior of the human immune system, where the dendritic cell has upwards of fifteen to twenty different indicators, called Toll-Like Receptors (TLRs), each one evolved to detect a specific feature or a small set of features. (e.g. one TLR has evolved to target features only found on the tuberculosis bacterium).
"Present applications of the DCA typically consider only one or two outputs of feature indicators. There has been very little development on combining feature indicators together to analyze the status of the environment or system. Instead, the DCA may use a mean of all the indicator outputs. As a result, one very 'strong' indicator output, also referred to herein as a 'strong' signal or even multiple 'strong' indicator outputs may be drowned out by a large number of 'nominal' indicator outputs, also referred to herein as 'nominal' signals."
Supplementing the background information on this patent, VerticalNews reporters also obtained the inventors' summary information for this patent: "The present disclosure is directed to a method and system that combines and weights multiple signal values that overcomes some of the problems and disadvantages discussed above.
"In one example, a system for the determination of a state of at least a portion of the system comprises a DCA module and a plurality of indicators, wherein each indicator generates a signal vector that indicates a state of an environment of the indicator. The DCA module receives the signal vectors from the plurality of indicators and combines the signal vectors to a combined single signal vector.
"The DCA module may use the DCA to analyze the combined single signal vector to determine a state of at least a portion of the system. Each signal vector may comprise a vector comprised of at least four floating point values. The four floating point values may correspond to a PAMP signal, a danger signal, a safe signal, and an inflammatory signal. The DCA module may sort the signal vectors from the plurality of indicators by the four floating point values. Each of the four floating point values may have an upper bound. The DCA module may weight each signal vector sorted by the four floating point values. The DCA module may further sort the signal vectors from largest to smallest. The DCA module may apply a different decay factor to each signal vector, the decay factor applied increases as applied from the largest signal to the smallest signal to weight each signal vector. Combining the signal vectors to the combined single signal vector may comprise adding together the weighted signal vectors.
"In another example, a method is disclosed for combining multiple signal values in a DCA. The method comprises receiving multiple signal vectors from a plurality of indicators, wherein the signals are received at a DCA module. The method comprises combining the multiple signal vectors into a single resultant vector. The multiple signal vectors may each be comprised of at least four floating point values. The four floating point values may correspond to a PAMP signal, a danger signal, a safe signal, and an inflammatory signal. The method may comprise sorting the received signal vectors into four groupings grouped by the four floating point values. The method may comprise weighting the sorted received signal vectors. The method may comprise using a decay factor to weight the sorted received signal vectors. The smallest decay factor may be assigned to a largest value for each group. The method may comprise increasing the decay factor assigned to each floating point value as the value decreases within each group. The decay factor may be exponentially increased as it is applied to each floating point value within each group."
For the URL and additional information on this patent, see: Handel, Mark Jonathan; Stuart, Douglas Alan; Taylor, Hugh L; Dorris, Steve A.; Wilson, Brett Michael. Method for Combining Multiple Signal Values in the Dendritic Cell Algorithm. U.S. Patent Number 9596259, filed November 5, 2014, and published online on March 14, 2017. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=9596259.PN.&OS=PN/9596259RS=PN/9596259
Keywords for this news article include: Antigen-Presenting Cells, Algorithms, Immunology, Dendritic Cells, THE BOEING COMPANY, Hemic and Immune Systems, Mononuclear Phagocyte System.
Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2017, NewsRx LLC