Deep neural networks are vulnerable to adversarial examples. While there are many methods for generating adversarial examples using neural networks, creating such examples with high perceptual quality and improved training remains an area of active research. In this paper, we propose the Iterative Training Attack (ITA), a black-box attack based on a perturbation generative network for generating adversarial examples. ITA generates such examples by randomly initializing the perturbation generative network multiple times, iteratively training and optimizing a refined loss function. Compared to other neural network-based attacks, our proposed method generates adversarial examples with higher attack rates and within a small perturbation range even when the advanced defense is employed. Despite being a black-box attack, ITA outperforms gradient-based white-box attacks even under basic standards. The authors evaluated their method on a TRADES robust model trained with the MNIST dataset and achieved a robust accuracy of 92.46%, the highest among the evaluated methods.
In this letter, a novel millimeter-wave chip packaging method based on flip-suspended-microstrip technology is proposed. The flip-suspendedmicrostrip contains a waveguide probe, a suspended microstrip line, input and output matching lines, and a terminal pad. The waveguide probe realizes energy coupling from the rectangular waveguide, and the terminal pad above the signal pad of chip achieves power transmission via electronic contact. Thus, the bonding wires which will bring parasitic inductance at high frequencies are avoided. To validate the proposed packaging method, back-toback modules with coplanar waveguide/low noise amplifier were fabricated.The measured insertion loss of the back-to-back transition with a 1.75-mmlong coplanar waveguide is 2.6-4.2 dB over the entire D-band, while the packaging loss of the low noise amplifier module with the back-to-back transition is less than 2.2 dB at 120-170 GHz, which indicate that the proposed broadband transition is feasible for millimeter-wave chip packaging.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.