Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimization (preprint)

Deep neural networks (DNNs) have achieved state-of-the-art performance on face recognition (FR) tasks in the last decade. In real scenarios, the deployment of DNNs requires taking various face accessories into consideration, like glasses, hats, and masks. In the COVID-19 pandemic era, wearing face masks is one of the most effective ways to defend against the novel coronavirus. However, DNNs are known to be vulnerable to adversarial examples with a small but elaborated perturbation. Thus, a facial mask with adversarial perturbations may pose a great threat to the widely used deep learning-based FR models. In this paper, we consider a challenging adversarial setting: targeted attack against FR models. We propose a new stealthy physical masked FR attack via adversarial style optimization. Specifically, we train an adversarial style mask generator that hides adversarial perturbations inside style masks. Moreover, to ameliorate the phenomenon of sub-optimization with one fixed style, we propose to discover the optimal style given a target through style optimization in a continuous relaxation manner. We simultaneously optimize the generator and the style selection for generating strong and stealthy adversarial style masks. We evaluated the effectiveness and transferability of our proposed method via extensive white-box and black-box digital experiments. Furthermore, we also conducted physical attack experiments against local FR models and online platforms.

Impacts of the COVID-19 Economic Slowdown on Soybean Crop Yields in the United States (preprint)

It is without question that the COVID-19 pandemic has taken its toll on the U.S. economy. Stay-at-home orders led to reduced vehicular traffic and widespread declines in anthropogenic emissions, such as nitrogen oxides (NOx) and surface ozone (O3). This study is the first to explore the potential consequences of O3 changes resulting from the economic shutdown in the United States on soybean crop yields for 2020. The pandemic’s impact on surface O3 is quantified using the NOAA’s National Air Quality Forecasting Capability (NAQFC), which is based on the Community Multi-Scale Air Quality (CMAQ) model for May-July 2020. The “would-be”, 2020 level business-as-usual (BAU) emissions are compared to a simulation that uses representative COVID-19 (C19) emissions. For each emissions scenario, crop exposures are calculated using the AOT40 cumulative exposure index and then combined with county-level soybean production totals to determine regional yield losses. Exposure changes ranged between -0.8 - 1.25 ppmVhr-1. It was further shown that increased exposures (0.5 – 1.25 ppmVhr-1) in the Southeast counteracted decreased exposures (0.8 – 0.5 ppmVhr-1) in other regions. As a result, corresponding yield improvements counteracted yield losses around the Mississippi River Valley and allowed for minimal soybean production loss totaling $4.7 million over CONUS.