Counter-fraud measures for an ATM device

1. A method, comprising:

monitoring, by an automated teller machine (ATM) device, a target area associated with the ATM device by capturing images of the target area using one or more image sensors,

the target area being associated with potentially fraudulent activity targeting the ATM device;

performing, by the ATM device and using a machine learning application that is trained to identify human body parts, image segmentation of one or more of the images to detect one or more conditions,

wherein the one or more conditions are associated with an indication of fraudulent activity, and

wherein the machine learning application is a deep learning network that is trained to perform image segmentation of human body parts by analyzing sequences of images in which fraudulent activity occurs;

detecting, by the ATM device, the one or more conditions;

generating, by the ATM device and based on detecting the one or more conditions, a fraud score associated with the one or more conditions;

determining, by the ATM device, whether the fraud score meets a threshold; and

performing, by the ATM device, one or more actions based on whether the fraud score meets the threshold.

2. The method of claim 1 , further comprising:

initiating a timer upon or after dispensing cash from an instrument dispenser associated with the ATM device;

determining that a portion of the cash remains at the instrument dispenser after expiration of the timer; and

detecting potentially fraudulent activity based on the determination.

3. The method of claim 1 , wherein performing the one or more actions comprises one or more of:

generating an audible alert and/or a visual alert,

instructing the one or more image sensors to capture additional images of the target area and/or of a vicinity of the ATM device,

deactivating the ATM device,

issuing a notification, that identifies the potentially fraudulent activity at the ATM device, to a local law enforcement authority and/or to an entity associated with the ATM device, or

causing a door associated with the ATM device to be temporarily locked.

4. The method of claim 1 , further comprising:

receiving input indicating that maintenance is to be performed on the ATM device; and

refraining from performing the one or more actions based on receiving the input.

5. The method of claim 1 , further comprising:

dispensing, via an instrument dispenser associated with an ATM machine, a plurality of instruments based on an ATM request; and

detecting that a body part is positioned proximate to the instrument dispenser after dispensing the plurality of instruments based on utilizing the machine learning application to perform segmentation of at least one image of an area surrounding the instrument dispenser,

wherein the machine learning application is associated with a neural network.

6. The method of claim 1 , wherein the target area includes at least one of:

a portion of an access panel of an enclosure of the ATM device; or

a portion of an enclosure, of the ATM device, proximate to an internal computing device of the ATM device.

7. The method of claim 1 , further comprising:

receiving data related to potential poses of a human hand; and

utilizing the data to generate multiple synthetic models of the human hand.

8. An automated teller machine (ATM) device, comprising:

one or more memories; and

one or more processors communicatively coupled to the one or more memories, configured to:

monitor a target area associated with the ATM device by capturing images of the target area using one or more image sensors,

the target area being associated with potentially fraudulent activity targeting the ATM device;

perform, using a machine learning application that is trained to identify human body parts, image segmentation of one or more of the images to detect one or more conditions,

wherein the one or more conditions are associated with an indication of fraudulent activity, and

wherein the machine learning application is a deep learning network that is trained to determine specific hand motions indicative of fraudulent activity associated with the ATM device;

detect the one or more conditions;

generate, based on detecting the one or more conditions, a fraud score associated with the one or more conditions;

determine whether the fraud score meets a threshold; and

perform, based on whether the fraud score meets the threshold, one or more actions.

9. The ATM device of claim 8 , wherein the one or more conditions include a first condition and a second condition, and

wherein the second condition is weighted differently than the first condition.

10. The ATM device of claim 8 , wherein the one or more processors are further configured to:

receive input indicating that maintenance is to be performed on the ATM device; and

refrain from performing the one or more actions based on receiving the input.

11. The ATM device of claim 8 , wherein the one or more processors are further configured to:

dispense, via an instrument dispenser associated with an ATM machine, a plurality of instruments based on an ATM request; and

detect that a body part is positioned proximate to the instrument dispenser after dispensing the plurality of instruments based on utilizing the machine learning application to perform segmentation of at least one image of an area surrounding the instrument dispenser,

wherein the machine learning application is associated with a neural network.

12. The ATM device of claim 8 , wherein the target area includes at least one of:

a portion of an access panel of an enclosure of the ATM device; or

a portion of an enclosure, of the ATM device, proximate to an internal computing device of the ATM device.

13. The ATM device of claim 8 , wherein the one or more processors are further configured to:

receive data related to potential poses of a human hand; and

utilize the data to generate multiple synthetic models of the human hand.

14. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors of an automated teller machine (ATM) device to:

receive a request to process an ATM transaction;

dispense, via an instrument dispenser output, a plurality of instruments based on the request;

perform, using a machine learning application that is trained to identify human body parts, image segmentation of one or more images to detect one or more conditions,

wherein the one or more conditions are associated with an indication of fraudulent activity, and

wherein the machine learning application is a deep learning network that is trained to perform image segmentation of human body parts by analyzing sequences of images in which fraudulent activity occurs;

detect, based on performing the image segmentation, that a user's hand approaches the instrument dispenser output after dispensing the plurality of instruments;

determine, after dispensing the plurality of instruments and after detecting the user's hand approaches the instrument dispenser output, that a portion of the plurality of instruments is present at the instrument dispenser output; and

perform one or more actions based on determining that a portion of the plurality of instruments is present at the instrument dispenser output.

15. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

initiate a timer upon or after dispensing the plurality of instruments from the instrument dispenser output;

determine that the portion of the plurality of instruments remains at the instrument dispenser output after expiration of the timer; and

detect potentially fraudulent activity based on the determination.

16. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, that cause the one or more processors to performing the one or more actions, cause the one or more processors to one or more of:

generate an audible alert and/or a visual alert,

deactivate the ATM device, or

issue a notification, that identifies potentially fraudulent activity at the ATM device, to a local law enforcement authority and/or to an entity associated with the ATM device.

17. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

receive input indicating that maintenance is to be performed on the ATM device; and

refrain from performing the one or more actions based on receiving the input.

18. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

detect that a body part is positioned proximate to the instrument dispenser after dispensing the plurality of instruments based on utilizing the machine learning application to perform segmentation of at least one image of an area surrounding the instrument dispenser,

wherein the machine learning application is associated with a neural network.

19. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

receive data related to potential poses of a human hand; and

utilize the data to generate multiple synthetic models of the human hand.

20. The non-transitory computer-readable medium of claim 14 , wherein the one or more conditions include a first condition and a second condition, and

wherein the second condition is weighted differently than the first condition.