Cyber security system utilizing interactions between detected and hypothesize cyber-incidents
An apparatus may include a set of modules and artificial intelligence models to detect a cyber incident, a simulator to simulate an actual cyber attack of the cyber incident on a network including physical devices being protected by the set of modules and artificial intelligence models; and a feedback loop between i) the set of modules and artificial intelligence models and ii) the simulator, during an ongoing detected cyber incident. An attack path modeling module is configured to feed details of the detected incident by a cyber threat module into an input module of the simulator, and to run one or more hypothetical simulations of that detected incident in order to predict and control an autonomous response to the detected incident. Any software instructions forming part of the set of modules, the artificial intelligence models, and the simulator are stored in an executable form in memories and executed by processors.
1 . An apparatus comprising:
a defined set of modules, including a cyber threat module and an autonomous response module, and one or more artificial intelligence models configured to detect and respond to a cyber incident, where the defined set of modules and the one or more artificial intelligence models are part of a cyber security appliance installed in a network, where the cyber threat module is configured to cooperate with the autonomous response module to cause one or more autonomous responses in response to be taken to counter a cyber threat that is part of the cyber incident, where the autonomous response module, rather than a human taking an action, is configured to cause the one or more autonomous responses in response to be taken to counter the cyber threat in the detected cyber incident;
a simulator configured to simulate an actual cyber attack of the cyber incident on the network, including physical devices, being protected by the set of modules and artificial intelligence models configured to detect the cyber incident;
a feedback loop between i) the set of modules and artificial intelligence models configured to detect the cyber incident and ii) the simulator configured to simulate the actual cyber attack of the cyber incident on the network including physical devices being protected by the set of modules and artificial intelligence models configured to detect the cyber incident during an ongoing detected cyber incident,
where an attack path modeling module is configured to feed details of the detected cyber incident by the cyber threat module into an input module of the simulator, where the simulator is configured to run one or more hypothetical simulations of that detected cyber incident and cooperate with the autonomous response module in order to predict and control the one or more autonomous responses to the detected cyber incident, and
where any software instructions forming part of the set of modules, the artificial intelligence models, and the simulator are stored in an executable form in one or more memories and executed by one or more processors.
2 . The apparatus of claim 1 ,
where the simulator is configured to construct a graph of a virtualized instance of the network including i) the physical devices connecting to the virtualized instance of the network as well as ii) connections and pathways through the virtualized instance of the network, and
where the set of modules in the cyber security appliance are configured to cooperate with the simulator to predict an initial autonomous response to the detected cyber incident and then how effectively the initial autonomous response performs in mitigating the detected cyber incident once the autonomous response module takes the initial autonomous response, where the initial autonomous response is visible to an attacker in the actual cyber attack, and the set of modules in the cyber security appliance are configured to cooperate with the simulator to predict how the attacker may possibly alter their plans in response to being detected and the initial autonomous response that is visible to the attacker.
3 . The apparatus of claim 2 , where the simulator is configured to run the one or more hypothetical simulations of the detected incident to calculate one or more paths of least resistance from the virtualized instance of a source device through to other virtualized instances of components of the network until reaching an end goal of each hypothetical simulation of the detected incident, but not calculate every theoretically possible path from the virtualized instance of the source device to the end goal of each hypothetical simulation of the detected incident.
4 . The apparatus of claim 1 , where the simulator is further configured to prioritize which devices connecting to a virtualized instance of the network should have a priority to allocate security resources to them based on results of the one or more hypothetical simulations of the detected incident, and
where the set of modules in the cyber security appliance are configured to cooperate with the simulator to predict an initial autonomous response to the detected cyber incident and then how effectively the initial autonomous response performs in mitigating the detected cyber incident once the autonomous response module takes the initial autonomous response, where the initial autonomous response is hidden to an attacker in the actual cyber attack.
5 . The apparatus of claim 2 , where the simulator is configured to construct the graph of the virtualized network, with its nets and subnets, where two or more of the devices connecting to the virtualized network are assigned with different weighting resistances to malicious compromise from the one or more hypothetical simulations based on the actual cyber attack of the cyber incident on the virtualized instance of the network.
6 . The apparatus of claim 1 , where the simulator is further configured to run a single hypothetical simulation based on the actual cyber attack of the cyber incident on a virtualized instance of the network in order to calculate a set of paths of possible cyber attack propagation in the network if no autonomous response action is taken in response to the actual cyber attack of the cyber incident.
7 . The apparatus of claim 6 , where the simulator is further configured to calculate, based at least in part on the results of the one or more hypothetical simulations, a risk score for each device, the risk score being indicative of a possible severity of a compromise if no autonomous response action is taken in response to the actual cyber attack of the cyber incident.
8 . The apparatus of claim 1 , where once the simulator runs the one or more hypothetical simulations, a pattern of life, conditions, and indicators in the network are recorded to show what indicators and level of detected cyber incident would have been needed to trigger the one or more autonomous responses.
9 . The apparatus of claim 1 , where the simulator is further configured to increase a risk score associated with a first device based at least in part on: a determination that the first device has been a target in past cyber attacks, the first device is in connection with a second device which is designated as essential to the network, and the first device is in connection with at least one device with a risk score over a pre-defined threshold risk score.
10 . The apparatus of claim 1 , where the simulator is configured to run the one or more hypothetical simulations of the detected incident to calculate one or more paths of least resistance for each hypothetical simulation to compromise 1) a virtualized instance of a source device, originally compromised by the cyber incident, 2) through to other virtualized instances of components of a virtualized network, 3) until reaching an end goal of that hypothetical simulation of the one or more hypothetical simulations in the virtualized network, all based on historic knowledge of connectivity and behavior patterns of users and devices within the network under analysis.
11 . A method for predicting one or more autonomous responses to a detected cyber incident, the method comprising:
configuring a defined set of modules, including a cyber threat module and an autonomous response module, and one or more artificial intelligence models configured to detect and respond to the cyber incident, where the defined set of modules and the one or more artificial intelligence models are part of a cyber security appliance installed in a network;
configuring the cyber threat module to cooperate with the autonomous response module to cause the one or more autonomous responses in response to be taken to counter a cyber threat that is part of the detected cyber incident, where the autonomous response module, rather than a human taking an action, is configured to cause the one or more autonomous responses in response to be taken to counter the cyber threat in the detected cyber incident;
configuring a simulator configured to simulate an actual cyber attack of the detected cyber incident on the network, including physical devices, being protected by the set of modules and artificial intelligence models configured to detect the cyber incident;
configuring a feedback loop between i) the set of modules and artificial intelligence models configured to detect the cyber incident and ii) the simulator configured to simulate the actual cyber attack of the cyber incident on the network including physical devices being protected by the set of modules and artificial intelligence models configured to detect the cyber incident during an ongoing detected cyber incident,
where an attack path modeling module is configured to feed details of the detected cyber incident by the cyber threat module into an input module of the simulator, where the simulator is configured to run one or more hypothetical simulations of that detected cyber incident and cooperate with the autonomous response module in order to predict and control the one or more autonomous responses to the detected cyber incident, and
where any software instructions forming part of the set of modules, the artificial intelligence models, and the simulator are stored in an executable form in one or more memories and executed by one or more processors.
12 . The method of claim 11 , further comprising
configuring the simulator to construct a graph of a virtualized instance of the network including i) the physical devices connecting to the virtualized instance of the network as well as ii) connections and pathways through the virtualized instance of the network.
13 . The method of claim 12 , further comprising
configuring the simulator to run the one or more hypothetical simulations of the detected incident to calculate one or more paths of least resistance from the virtualized instance of a source device through to other virtualized instances of components of the network until reaching an end goal of each hypothetical simulation of the detected incident, but not calculate every theoretically possible path from the virtualized instance of the source device to the end goal of each hypothetical simulation of the detected incident.
14 . The method of claim 11 , further comprising
configuring the simulator to prioritize which devices connecting to a virtualized instance of the network should have a priority to allocate security resources to them based on results of the one or more hypothetical simulations of the detected incident.
15 . The method of claim 12 , further comprising
configuring the simulator to construct the graph of the virtualized network, with its nets and subnets, where two or more of the devices connecting to the virtualized network are assigned with different weighting resistances to malicious compromise from the one or more hypothetical simulations based on the actual cyber attack of the cyber incident on the virtualized instance of the network; and
running a single hypothetical simulation based on the actual cyber attack of the cyber incident on the virtualized instance of the network in order to calculate a set of paths of possible cyber attack propagation in the network if no autonomous response action is taken in response to the actual cyber attack of the cyber incident.
16 . The method of claim 15 , further comprising
configuring the simulator to calculate, based at least in part on the results of the one or more hypothetical simulations, a risk score for each device, the risk score being indicative of a possible severity of the compromise if no autonomous response action is taken in response to the actual cyber attack of the cyber incident.
17 . The method of claim 11 , where once the simulator runs the one or more hypothetical simulations, a pattern of life, conditions, and indicators in the network are recorded to show what indicators and level of detected cyber incident would have been needed to trigger the autonomous response action.
18 . The method of claim 11 , further comprising
configuring the simulator to increase a risk score associated with a first device based at least in part on: a determination that the first device has been a target in past cyber attacks, the first device is in connection with a second device which is designated as essential to the network, and the first device is in connection with at least one device with the risk score over a pre-defined threshold risk score.
19 . The method of claim 11 , further comprising
configuring the simulator to run the one or more hypothetical simulations of the detected incident to calculate one or more paths of least resistance for each hypothetical simulation to compromise 1) a virtualized instance of a source device, originally compromised by the cyber incident, 2) through to other virtualized instances of components of a virtualized network, 3) until reaching an end goal of that hypothetical simulation of the one or more hypothetical simulations in the virtualized network, all based on historic knowledge of connectivity and behavior patterns of users and devices within the network under analysis.
20 . A non-transitory computer readable medium in an apparatus, comprising one or more computer readable codes operable, when executed by one or more processors, to instruct the apparatus to perform the method of claim 11 .