Science Daily April 4, 2019
To understand and document vulnerabilities in deep and machine-learning algorithms, researchers at the Southwestern Research Institute have developed patterns when worn or mounted on a vehicle, cause the algorithms in the camera to either misclassify or mislocate objects, creating a vulnerability. Malicious parties could place these patterns near roadways, potentially creating chaos for vehicles equipped with object detectors.
The researchers call these patterns ‘perception invariant’ adversarial examples because they don’t need to cover the entire object or be parallel to the camera to trick the algorithm. The algorithms can misclassify the object as long as they sense some part of the pattern. The team has created a framework capable of repeatedly testing these attacks against a variety of deep-learning detection programs which will be extremely useful for testing solutions. The technique mitigates the risk for compromise in automated image processing systems…read more.
Credit: Southwest Research Institute. First bacterial genome created entirely with a computer https://www.sciencedaily.com/releases/2019/04/190401171343.htm