Domain generalization is proposed to address distribution shift, arising from statistical disparities between training source and unseen target domains. The widely used first-order meta-learning algorithms demonstrate strong performance for domain generalization by leveraging the gradient matching theory, which aims to establish balanced parameters across source domains to reduce overfitting to any particular domain. However, our analysis reveals that there are actually numerous directions to achieve gradient matching, with current methods representing just one possible path. These methods actually overlook another critical factor that the balanced parameters should be close to the centroid of optimal parameters of each source domain. To address this, we propose a simple yet effective arithmetic meta-learning with arithmetic-weighted gradients. This approach, while adhering to the principles of gradient matching, promotes a more precise balance by estimating the centroid between domain-specific optimal parameters. Experimental results validate the effectiveness of our strategy. Our code is available at https://github.com/zzwdx/ARITH.

Nowadays, the proliferation of open Internet of Things (IoT) devices has made IoT systems increasingly vulnerable to cyber attacks. It is of great practical significance to solve the security issues of IoT systems. Drawing inspiration from the concept of “Pawn Promotion” in chess, this article proposes a cyber deception defense system based on “Chess Puzzle” (CP-CDD), which enhances the security of IoT systems by continuously changing the real and fake attributes of services. First, we design a distributed election control device scheme to address the security concerns arising from centralized control in the IoT system. Second, we introduce an adaptive differential evolution cyber deception strategy (ADECDS) optimization method, aiming to derive effective cyber deception defense strategies for the CP-CDD system. Specifically, we design two key components of cyber deception strategy evolution: 1) service strategy coding and 2) fitness function, and describe the ADECDS algorithm. Finally, the security and effectiveness of the CP-CDD system is proven through attack and defense experiments conducted in a real-world environment.

Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains. However, most current methods do not account for a common realistic scenario where the source and target domains have different classes. To overcome this deficiency, open set domain generalization (OSDG) then emerges as a more practical setting to recognize unseen classes in unseen domains. An intuitive approach is to use multiple one-vs-all classifiers to define decision boundaries for each class and reject the outliers as unknown. However, the significant class imbalance between positive and negative samples often causes the boundaries biased towards positive ones, resulting in misclassification for known samples in the unseen target domain. In this paper, we propose a novel meta-learning-based framework called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC), which considers gradient matching towards inter-domain and inter-class splits simultaneously to find a generalizable boundary balanced for all tasks. Experimental results demonstrate that MEDIC not only outperforms previous methods in open set scenarios, but also maintains competitive close set generalization ability at the same time. Our code is available at https://github.com/zzwdx/MEDIC.

Plug-and-Play ADMM is a recently developed variation of the classical ADMM algorithm that replaces one of the subproblems using an off-the-shelf image denoiser. Despite its apparently ad-hoc nature, Plug-and-Play ADMM produces surprisingly good image recovery results. However, since in Plug-and-Play ADMM the denoiser is treated as a black-box, behavior of the overall algorithm is largely unknown. In particular, the internal parameter that controls the rate of convergence of the algorithm has to be adjusted by the user, and a bad choice of the parameter can lead to severe degradation of the result. In this paper, we present a parameter-free Plug-and-Play ADMMwhere internal parameters are updated as part of the optimization. Our algorithm is derived from the generalized approximate message passing, with several essential modifications. Experimentally, we find that the new algorithm produces solutions along a reliable and fast converging path.