Detection of cyber machinery attacks

1. A method of cyber protection of a machine, comprising:

acquiring acoustic signals from a vicinity of a machine, while the machine is operative;

receiving information on a software behavior of a controller of the machine;

calculating a suspicion score indicative of a probability that the machine is operating under instructions of malware on the controller, as a function of both the acquired acoustic signals and the received information on the software behavior; and

performing a protective measure in response to a determination that the calculated suspicion score is indicative of a possible cyber attack,

wherein receiving information on the software behavior of the controller comprises receiving information on resource utilization of the controller and wherein calculating the suspicion score comprises calculating the suspicion score as a function of both the acquired acoustic signals and the received information on resource utilization of the controller.

2. The method of claim 1 , wherein receiving information on the software behavior of the controller comprises receiving a cyber suspicion score calculated separately and wherein calculating the suspicion score comprises calculating the suspicion score as a function of both the acquired acoustic signals and the received cyber suspicion score calculated separately.

3. The method of claim 1 , wherein calculating the suspicion score comprises applying a single machine learning algorithm to both the acquired acoustic signals and the received information on the software behavior of the controller.

4. The method of claim 1 , wherein acquiring the acoustic signals comprises acquiring by an acoustic monitor not connected to the controller in a manner allowing data or instructions to be passed from the controller to the acoustic monitor.

5. The method of claim 1 , wherein receiving information on the software behavior of the controller comprises receiving communication logs of the controller.

6. The method of claim 1 , wherein calculating the suspicion score comprises applying a machine learning algorithm to the acquired acoustic signals.

7. The method of claim 1 , wherein performing the protective measure comprises performing a cyber scan of the controller.

8. A method of cyber protection of a machine, comprising:

acquiring acoustic signals from a vicinity of a machine, while the machine is operative;

receiving information on a software behavior of a controller of the machine;

calculating a suspicion score indicative of a probability that the machine is operating under instructions of malware on the controller, as a function of both the acquired acoustic signals and the received information on the software behavior; and

performing a protective measure in response to a determination that the calculated suspicion score is indicative of a possible cyber attack,

wherein receiving information on the software behavior of the controller comprises receiving a cyber suspicion score calculated separately and wherein calculating the suspicion score comprises calculating the suspicion score as a function of both the acquired acoustic signals and the received cyber suspicion score calculated separately,

wherein calculating the suspicion score comprises analyzing the acquired acoustic signals to assign an acoustic suspicion score and calculating the suspicion score as a function of both the acoustic suspicion score and the received cyber suspicion score.

9. The method of claim 8 , wherein analyzing the acquired acoustic signals to assign the acoustic suspicion score comprises analyzing the acquired acoustic signals, by a processor, to calculate values of one or more operation parameters of the machine from the acquired acoustic signals and comparing the values of the one or more operation parameters calculated by the processor to corresponding values received from the controller.

10. The method of claim 8 , wherein analyzing the acquired acoustic signals to assign the acoustic suspicion score comprises analyzing the acquired acoustic signals, to identify changes in the acoustic signals over time and analyzing the identified changes to check whether the changes have one or more characteristics indicative of intentional changes.

11. The method of claim 8 , wherein calculating the suspicion score comprises calculating a weighted sum of the acoustic suspicion score and the received cyber suspicion score.

12. The method of claim 11 , wherein the weight of the acoustic suspicion score in the weighted sum depends on a quality of the acoustic signals.

13. The method of claim 8 , wherein receiving information on the software behavior of the controller comprises receiving communication logs of the controller.

14. The method of claim 8 , wherein calculating the suspicion score comprises applying a machine learning algorithm to the acquired acoustic signals.

15. An apparatus for cyber protection of a machine, comprising:

a microphone for acquiring acoustic signals from a vicinity of a machine controlled by a controller, while the machine is operative;

an interface connecting to a controller of the machine and

a processor configured to analyze acoustic signals acquired by the microphone, to determine whether the machine is operating suspiciously, to receive information on a software behavior of a controller of the machine through the interface, and to calculate a suspicion score indicative of a probability that the machine is operating under instructions of malware on the controller, as a function of both the acquired acoustic signals and the received information on the software behavior,

wherein the processor is configured to initiate a protective measure in response to a determination that the calculated suspicion score is indicative of a possible cyber attack,

wherein the processor is configured to analyze the acquired acoustic signals by analyzing the acquired acoustic signals, to identify changes in the acoustic signals over time and analyzing the identified changes to check whether the changes have one or more characteristics indicative of intentional changes.

16. The apparatus of claim 15 , wherein the microphone is not connected to the controller or the machine.

17. The apparatus of claim 15 , wherein the processor is configured to analyze the acquired acoustic signals by calculating values of one or more operation parameters of the machine from the acquired acoustic signals and comparing the values of the one or more operation parameters calculated by the processor to corresponding values received from the controller.

18. The apparatus of claim 15 , wherein the processor is configured to calculate the suspicion score by applying a single machine learning algorithm to both the acquired acoustic signals and the received information on the software behavior of the controller.

19. An apparatus for cyber protection of a machine, comprising:

a microphone for acquiring acoustic signals from a vicinity of a machine controlled by a controller, while the machine is operative;

an interface connecting to a controller of the machine and

a processor configured to analyze acoustic signals acquired by the microphone, to determine whether the machine is operating suspiciously, to receive information on a software behavior of a controller of the machine through the interface, and to calculate a suspicion score indicative of a probability that the machine is operating under instructions of malware on the controller, as a function of both the acquired acoustic signals and the received information on the software behavior,

wherein the processor is configured to initiate a protective measure in response to a determination that the calculated suspicion score is indicative of a possible cyber attack,

wherein the processor is configured to separately calculate a cyber suspicion score and an acoustic suspicion score and to calculate the suspicion score as a function of both the acoustic suspicion score and the cyber suspicion score.

20. An apparatus for cyber protection of a machine, comprising:

a microphone for acquiring acoustic signals from a vicinity of a machine controlled by a controller, while the machine is operative;

an interface connecting to a controller of the machine and

a processor configured to analyze acoustic signals acquired by the microphone, to determine whether the machine is operating suspiciously, to receive information on a software behavior of a controller of the machine through the interface, and to calculate a suspicion score indicative of a probability that the machine is operating under instructions of malware on the controller, as a function of both the acquired acoustic signals and the received information on the software behavior,

wherein the processor is configured to initiate a protective measure in response to a determination that the calculated suspicion score is indicative of a possible cyber attack,

wherein the processor is configured to receive information on resource utilization of the controller and to calculate the suspicion score as a function of both the acquired acoustic signals and the received information on resource utilization of the controller.