Abstract: Concepts and technologies disclosed herein are directed to image classification attack mitigation. According to one aspect of the concepts and technologies disclosed herein, a system can obtain an original image and reduce a resolution of the original image to create a reduced resolution image. The system can classify the reduced resolution image and output a first classification. The system also can classify the original image via deep learning image classification and output a second classification. The system can compare the first classification and the second classification. In response to determining that the first classification and the second classification match, the system can output the second classification of the original image. In response to determining that the first classification and the second classification do not match, the system can output the first classification of the original image.

Abstract: Example methods and systems are disclosed to provide autonomous vehicle sensor security. An example method may include generating, by a first autonomous vehicle, a first map instance of a physical environment using first environmental information generated by a first sensor of a first autonomous vehicle. A second map instance from at least one of a second autonomous vehicle located in the physical environment is received. The first map instance may be correlated with the second map instance. In response to a discrepancy between the first map instance and the second map instance, a secure sensor may be activated to generate a third map instance. In response to the third map instance verifying that the discrepancy accurately describes the physical environment, the first environmental information including the discrepancy is used to navigate the first autonomous vehicle.

Abstract: Concepts and technologies disclosed herein are directed to image classification attack mitigation. According to one aspect of the concepts and technologies disclosed herein, a system can obtain an original image and reduce a resolution of the original image to create a reduced resolution image. The system can classify the reduced resolution image and output a first classification. The system also can classify the original image via deep learning image classification and output a second classification. The system can compare the first classification and the second classification. In response to determining that the first classification and the second classification match, the system can output the second classification of the original image. In response to determining that the first classification and the second classification do not match, the system can output the first classification of the original image.

Abstract: Example methods and systems are disclosed to provide autonomous vehicle sensor security. An example method may include generating, by a first autonomous vehicle, a first map instance of a physical environment using first environmental information generated by a first sensor of a first autonomous vehicle. A second map instance from at least one of a second autonomous vehicle located in the physical environment is received. The first map instance may be correlated with the second map instance. In response to a discrepancy between the first map instance and the second map instance, a secure sensor may be activated to generate a third map instance. In response to the third map instance verifying that the discrepancy accurately describes the physical environment, the first environmental information including the discrepancy is used to navigate the first autonomous vehicle.

Abstract: Security mechanisms for content delivery networks (“CDNs”) are disclosed herein. One security mechanism can be used to mitigate or prevent dynamic content attacks. A system can execute a CDN manager to perform operations. In particular, the CDN manager can receive a plurality of hypertext transfer protocol (“HTTP”) requests, and parse a plurality of headers from the plurality of HTTP requests to determine a plurality uniform resource locators (“URLs”). The CDN manager can generate a plurality of web page images associated with the plurality of URLs. The CDN manager can execute a machine learning algorithm, such as a convolution neural network, to perform an analysis of the plurality of web page images. Based upon the analysis of the plurality of web page images, the CDN manager can determine whether the plurality of HTTP requests are for the same web page, which can be indicative of a dynamic content attack.

Abstract: Concepts and technologies disclosed herein are directed to image classification attack mitigation. According to one aspect of the concepts and technologies disclosed herein, a system can obtain an original image and reduce a resolution of the original image to create a reduced resolution image. The system can classify the reduced resolution image and output a first classification. The system also can classify the original image via deep learning image classification and output a second classification. The system can compare the first classification and the second classification. In response to determining that the first classification and the second classification match, the system can output the second classification of the original image. In response to determining that the first classification and the second classification do not match, the system can output the first classification of the original image.

Abstract: Security mechanisms for content delivery networks (“CDNs”) are disclosed herein. One security mechanism can be used to mitigate or prevent dynamic content attacks. A system can execute a CDN manager to perform operations. In particular, the CDN manager can receive a plurality of hypertext transfer protocol (“HTTP”) requests, and parse a plurality of headers from the plurality of HTTP requests to determine a plurality uniform resource locators (“URLs”). The CDN manager can generate a plurality of web page images associated with the plurality of URLs. The CDN manager can execute a machine learning algorithm, such as a convolution neural network, to perform an analysis of the plurality of web page images. Based upon the analysis of the plurality of web page images, the CDN manager can determine whether the plurality of HTTP requests are for the same web page, which can be indicative of a dynamic content attack.

Abstract: The concepts and technologies disclosed herein are directed to virtual machine (“VM”) orchestration spoofing attack mitigation. According to one aspect disclosed herein, an anti-spoofing controller (“ASC”) can determine a target memory location in which to instantiate a new VM. The ASC can determine a challenge for a physically unclonable function (“PUF”) associated with the target memory location. The ASC can provide the challenge to the PUF, and in response, can receive and store an output value from the PUF. The ASC can instruct an orchestrator to instantiate the new VM in the target memory location. The ASC can provide the challenge to the new VM, which can forward the challenge to the orchestrator. The ASC can receive, from the orchestrator, a response to the challenge, and can determine whether the response passes the challenge. If the response does not pass the challenge, the ASC can decommission the orchestrator.

Abstract: Concepts and technologies disclosed herein are directed to image classification attack mitigation. According to one aspect of the concepts and technologies disclosed herein, a system can obtain an original image and reduce a resolution of the original image to create a reduced resolution image. The system can classify the reduced resolution image and output a first classification. The system also can classify the original image via deep learning image classification and output a second classification. The system can compare the first classification and the second classification. In response to determining that the first classification and the second classification match, the system can output the second classification of the original image. In response to determining that the first classification and the second classification do not match, the system can output the first classification of the original image.

Abstract: Security mechanisms for content delivery networks (“CDNs”) are disclosed herein. One security mechanism can be used to mitigate or prevent dynamic content attacks. A system can execute a CDN manager to perform operations. In particular, the CDN manager can receive a plurality of hypertext transfer protocol (“HTTP”) requests, and parse a plurality of headers from the plurality of HTTP requests to determine a plurality uniform resource locators (“URLs”). The CDN manager can generate a plurality of web page images associated with the plurality of URLs. The CDN manager can execute a machine learning algorithm, such as a convolution neural network, to perform an analysis of the plurality of web page images. Based upon the analysis of the plurality of web page images, the CDN manager can determine whether the plurality of HTTP requests are for the same web page, which can be indicative of a dynamic content attack.

Abstract: The concepts and technologies disclosed herein are directed to security de-escalation for data access. A user device can define a security de-escalation rule. The user device can define a multi-tiered security zone within a user device file system utilized by a memory of the user device. The multi-tiered security zone can include a plurality of security tiers. The user device can identify data for de-escalation in accordance with the security de-escalation rule. The user device can de-escalate the data to generate de-escalated data by storing the data identified for de-escalation in a less secure security tier of the plurality of security tiers of the multi-tiered security zone. The user device can receive a data access request from an external user device. The user device can verify a data access credential contained in the data access request. The user device can provide the de-escalated data to the external user device.

Abstract: Example methods and systems are disclosed to provide autonomous vehicle sensor security. An example method may include generating, by a first autonomous vehicle, a first map instance of a physical environment using first environmental information generated by a first sensor of a first autonomous vehicle. A second map instance from at least one of a second autonomous vehicle located in the physical environment is received. The first map instance may be correlated with the second map instance. In response to a discrepancy between the first map instance and the second map instance, a secure sensor may be activated to generate a third map instance. In response to the third map instance verifying that the discrepancy accurately describes the physical environment, the first environmental information including the discrepancy is used to navigate the first autonomous vehicle.

Abstract: The concepts and technologies disclosed herein are directed to security de-escalation for data access. A user device can define a security de-escalation rule. The user device can define a multi-tiered security zone within a user device file system utilized by a memory of the user device. The multi-tiered security zone can include a plurality of security tiers. The user device can identify data for de-escalation in accordance with the security de-escalation rule. The user device can de-escalate the data to generate de-escalated data by storing the data identified for de-escalation in a less secure security tier of the plurality of security tiers of the multi-tiered security zone. The user device can receive a data access request from an external user device. The user device can verify a data access credential contained in the data access request. The user device can provide the de-escalated data to the external user device.

Abstract: Example methods and systems are disclosed to provide autonomous vehicle sensor security. An example method may include generating, by a first autonomous vehicle, a first map instance of a physical environment using first environmental information generated by a first sensor of a first autonomous vehicle. A second map instance from at least one of a second autonomous vehicle located in the physical environment is received. The first map instance may be correlated with the second map instance. In response to a discrepancy between the first map instance and the second map instance, a secure sensor may be activated to generate a third map instance. In response to the third map instance verifying that the discrepancy accurately describes the physical environment, the first environmental information including the discrepancy is used to navigate the first autonomous vehicle.

Abstract: Example methods and systems are disclosed to provide autonomous vehicle sensor security. An example method may include generating, by a first autonomous vehicle, a first map instance of a physical environment using first environmental information generated by a first sensor of a first autonomous vehicle. A second map instance from at least one of a second autonomous vehicle located in the physical environment is received. The first map instance may be correlated with the second map instance. In response to a discrepancy between the first map instance and the second map instance, a secure sensor may be activated to generate a third map instance. In response to the third map instance verifying that the discrepancy accurately describes the physical environment, the first environmental information including the discrepancy is used to navigate the first autonomous vehicle.

Abstract: A digital camera accesses, processes and displays a combination image composed of visible light and near non-visible (“NNV”) light. A method can include accessing, by a digital camera, raw data having first information associated with a first electromagnetic spectrum range and second information associated with a second electromagnetic spectrum range. The first electromagnetic spectrum range is substantially within the visible spectrum and the second electromagnetic spectrum range is substantially within the NNV spectrum. The method can also include optimizing the raw data for the visible spectrum, thereby generating a first visual image representation, and optimizing the raw data for the NNV spectrum, thereby generating a second visual image representation. The method can also include combining the first visual image representation and the second visual image representation to generate a combination image. The digital camera can then initiate the display of the combination image.

Abstract: A digital camera accesses, processes and displays a combination image composed of visible light and near non-visible (“NNV”) light. A method can include accessing, by a digital camera, raw data having first information associated with a first electromagnetic spectrum range and second information associated with a second electromagnetic spectrum range. The first electromagnetic spectrum range is substantially within the visible spectrum and the second electromagnetic spectrum range is substantially within the NNV spectrum. The method can also include optimizing the raw data for the visible spectrum, thereby generating a first visual image representation, and optimizing the raw data for the NNV spectrum, thereby generating a second visual image representation. The method can also include combining the first visual image representation and the second visual image representation to generate a combination image. The digital camera can then initiate the display of the combination image.

Abstract: A digital camera accesses, processes and displays a combination image composed of visible light and near non-visible (“NNV”) light. A method can include accessing, by a digital camera, raw data having first information associated with a first electromagnetic spectrum range and second information associated with a second electromagnetic spectrum range. The first electromagnetic spectrum range is substantially within the visible spectrum and the second electromagnetic spectrum range is substantially within the NNV spectrum. The method can also include optimizing the raw data for the visible spectrum, thereby generating a first visual image representation, and optimizing the raw data for the NNV spectrum, thereby generating a second visual image representation. The method can also include combining the first visual image representation and the second visual image representation to generate a combination image. The digital camera can then initiate the display of the combination image.

Abstract: A digital camera accesses, processes and displays a combination image composed of visible light and near non-visible (“NNV”) light. A method can include accessing, by a digital camera, raw data having first information associated with a first electromagnetic spectrum range and second information associated with a second electromagnetic spectrum range. The first electromagnetic spectrum range is substantially within the visible spectrum and the second electromagnetic spectrum range is substantially within the NNV spectrum. The method can also include optimizing the raw data for the visible spectrum, thereby generating a first visual image representation, and optimizing the raw data for the NNV spectrum, thereby generating a second visual image representation. The method can also include combining the first visual image representation and the second visual image representation to generate a combination image. The digital camera can then initiate the display of the combination image.

Abstract: A digital camera accesses, processes and displays a combination image composed of visible light and near non-visible (“NNV”) light. A method can include accessing, by a digital camera, raw data having first information associated with a first electromagnetic spectrum range and second information associated with a second electromagnetic spectrum range. The first electromagnetic spectrum range is substantially within the visible spectrum and the second electromagnetic spectrum range is substantially within the NNV spectrum. The method can also include optimizing the raw data for the visible spectrum, thereby generating a first visual image representation, and optimizing the raw data for the NNV spectrum, thereby generating a second visual image representation. The method can also include combining the first visual image representation and the second visual image representation to generate a combination image. The digital camera can then initiate the display of the combination image.