In this paper, we study the adversarial robustness of deep neural networks (DNN) for classification against optimal classifiers. We look at the smallest magnitude of possible additive perturbations that can change a classifier's output. We provide a matrix-theoretic explanation of the adversarial fragility of DNNs for classification. In particular, our theoretical results show that the adversarial robustness of a neural network can degrade as the input dimension d increases. Analytically, we show that the adversarial robustness of neural networks can be only 1/√d of the best possible adversarial robustness of optimal classifiers. Our theories match remarkably well with empirical results. The matrix-theoretic explanation aligns with an earlier information-theoretic feature-compression-based explanation for the adversarial fragility of neural networks.

Robust fish weight estimation is vital for sustainable fisheries, preventing overfishing and conserving resources, yet traditional methods are prone to environmental factors causing significant errors. To address the challenge, a vision-based fish weight estimation model is proposed, which generates a half-fish three dimensional point cloud from multi-angle images using neural radiance fields (NeRF), then applies bayesian optimization to identify the optimal hyperplane for full-fish reconstruction. This process estimates the fish volume, which is subsequently used to predict its weight through a generalized linear model. During the validation of the established dataset, the proposed method demonstrates remarkable performance with a mean square error of 0.007, root mean square error of 0.084 and a mean absolute error of 0.070, highlight its considerable application potential.

The multi-agent reinforcement learning systems (MARL) based on the Markov decision process (MDP) have emerged in many critical applications. To improve the robust-ness/defense of MARL systems against adversarial attacks, the study of various adversarial attacks on reinforcement learning systems is very important. Previous works on adversarial attacks considered some possible features to attack in MDP, such as the action poisoning attacks, the reward poisoning attacks, and the state perception attacks. In this paper, we propose a brand-new form of attack called the camouflage attack in the MARL systems. In the camouflage attack, the attackers change the appearances of some objects without changing the actual objects themselves; and the camouflaged appearances may look the same to all the targeted recipient (victim) agents. The camouflaged appearances can mislead the recipient agents to misguided actions. We design algorithms that give the optimal camouflage attacks minimizing the rewards of recipient agents. Our numerical and theoretical results show that camouflage attacks can rival the more con-ventional, but likely more difficult state perception attacks. We also investigate cost-constrained camouflage attacks and showed numerically how cost budgets affect the attack performance.

Multitask learning combines both commons among a group of tasks and each task's individual characters to achieve better performance. However, different tasks may lead to contrary gradient directions or imbalance gradient values disrupting the training process. We propose a new regularization algorithm based on multitask local Rademacher complexity called MultiDrop, dropping some random tasks in optimization. A new regularization function has been derived based on the upper bound of local Rademacher complexity in multitask learning. Experiments on different image classification datasets have been implemented to demonstrate the effectiveness of MultiDrop compared with other regularization algorithms, and links between theoretical analyses and experiments.

In neural networks, developing regularization algorithms to settle overfitting is one of the major study areas. We propose a new approach for the regularization of neural networks by the local Rademacher complexity called LocalDrop. A new regularization function for both fully-connected networks (FCNs) and convolutional neural networks (CNNs), including drop rates and weight matrices, has been developed based on the proposed upper bound of the local Rademacher complexity by the strict mathematical deduction. The analyses of dropout in FCNs and DropBlock in CNNs with keep rate matrices in different layers are also included in the complexity analyses. With the new regularization function, we establish a two-stage procedure to obtain the optimal keep rate matrix and weight matrix to realize the whole training model. Extensive experiments have been conducted to demonstrate the effectiveness of LocalDrop in different models by comparing it with several algorithms and the effects of different hyperparameters on the final performances.

Incoherent scatter radar (ISR) is the only ground-based instrument that can detect space plasma parameters from tens to thousands of kilometers above the earth. The Prototype Incoherent Scatter Radar System of Nanchang University, a versatile space detection radar, will be built at Nanchang University to detect the ionosphere over China in the end of 2013. Software-defined radio (SDR)-based and active phased antenna array are the two most significant features of this radar system. It can probe real time plasma parameters in the altitude range of the ionosphere (80-400 km) according to simulation. The novel ISR introduced in this letter has the advantages of low power, low cost, and modularization. When properly configurated, this system can also carry out coherent scatter detection and wind profile detection. Successful development of such an ISR will resolve the problem of continuous detection of ionospheric electric field and other parameters. This letter introduces the design of this software defined ISR prototype system.