No abstract

Achieving seed germination quality standards poses a real challenge to seed companies as they are compelled to abide by strict certification rules, while having only partial seed separation solutions at their disposal. This discrepancy results with wasteful disqualification of seed lots holding considerable amounts of good seeds and further translates to financial losses and supply chain insecurity. Here, we present the first-ever generic germination prediction technology that is based on deep learning and RGB image data and facilitates seed classification by seed germinability and usability, two facets of germination fate. We show technology competence to render dozens of disqualified seed lots of seven vegetable crops, representing different genetics and production pipelines, industrially appropriate, and to adequately classify lots by utilizing available crop-level image data, instead of lot-specific data. These achievements constitute a major milestone in the deployment of this technology for industrial seed sorting by germination fate for multiple crops.

This work proposes substantial algorithmic enhancements to the SPEA attack of Schlösser et al. [16] by adding cryptographic postprocessing, and improved signal processing to the photonic measurement phase. Our improved approach provides three crucial benefits: (1) For some SBox/SRAM configurations the original SPEA method is unable to identify a unique key, and terminates with up to 2 48 key candidates; using our new solver we are able to find the correct key regardless of the respective SBox/SRAM configuration. (2) Our methods reduce the number of required (complex photonic) measurements by an order of magnitude, thereby shortening the duration of the attack significantly. (3) Due to the unavailability of the attack equipment of Schlösser et al. [16] we additionally developed a novel Photonic Emission Simulator which we matched against the real equipment of the original SPEA work. With this simulator we were able to verify our enhanced SPEA attack by a full AES recovery which uses only a small number of photonic measurements.