Accurate prediction of Sea Surface Temperature (SST) is critical for understanding marine phenomena, studying climate dynamics, and forecasting environmental changes. However, SST time series exhibit varying trends across different regions due to differences in latitude, ocean currents, and depth, which complicates precise forecasting. To address this, our proposed framework, the Dynamic Scale Interaction Network (DSIN), dynamically adapts to these regional variations by selecting appropriate temporal scales in the frequency domain. This process is facilitated by a dynamic routing module that does not require the predefinition of scale numbers, enabling our model to generalize across diverse geographic areas with varying SST trends. Additionally, SST is significantly influenced by local climate phenomena, such as storms, making the modeling process more complex. DSIN addresses this challenge by incorporating multivariate interactions and leveraging a cross-attention mechanism to capture the correlations between SST and exogenous variables, such as storm data. This enhances the model’s ability to accurately forecast SST even under the influence of localized climate events. Moreover, to enhance the model’s adaptability to complex spatiotemporal dynamics and improve its robustness across different SST prediction tasks, the framework employs a Graph Neural Network (GNN) to capture intricate correlations. By incorporating a probabilistic loss function, we estimate the uncertainty of SST predictions, thereby providing valuable information for more informed decision-making in climate modeling, marine navigation, and fisheries management. Extensive experiments conducted on the OISST SST dataset demonstrate that DSIN consistently outperforms state-of-the-art methods, proving its superiority in SST prediction.

Scalable service-Oriented Middleware over IP (SOME/IP) is an Ethernet communication standard protocol in the Automotive Open System Architecture (AUTOSAR), promoting ECU-to-ECU communication over the IP stack. However, SOME/IP lacks a robust security architecture, making it susceptible to potential attacks. Besides, random hardware failure of ECU will disrupt SOME/IP communication. In this paper, we propose SISSA, a SOME/IP communication traffic-based approach for modeling and analyzing in-vehicle functional safety and cyber security. Specifically, SISSA models hardware failures with the Weibull distribution and addresses five potential attacks on SOME/IP communication, including Distributed Denial-of-Services, Man-in-the-Middle, and abnormal communication processes, assuming a malicious user accesses the in-vehicle network. Subsequently, SISSA designs a series of deep learning models with various backbones to extract features from SOME/IP sessions among ECUs. We adopt residual self-attention to accelerate the model’s convergence and enhance detection accuracy, determining whether an ECU is under attack, facing functional failure, or operating normally. Additionally, we have created and annotated a dataset encompassing various classes, including indicators of attack, functionality, and normalcy. This contribution is noteworthy due to the scarcity of publicly accessible datasets with such characteristics. Extensive experimental results show the effectiveness and efficiency of SISSA.

In this paper, 2×2 zero-sum games are studied under the following assumptions: (1) One of the players (the leader) commits to choose its actions by sampling a given probability measure (strategy); (2) The leader announces its action, which is observed by its opponent (the follower) through a binary channel; and (3) the follower chooses its strategy based on the knowledge of the leader’s strategy and the noisy observation of the leader’s action. Under these conditions, the equilibrium is shown to always exist. Interestingly, even subject to noise, observing the actions of the leader is shown to be either beneficial or immaterial for the follower. More specifically, the payoff at the equilibrium of this game is upper bounded by the payoff at the Stackelberg equilibrium (SE) in pure strategies; and lower bounded by the payoff at the Nash equilibrium, which is equivalent to the SE in mixed strategies. Finally, necessary and sufficient conditions for observing the payoff at equilibrium to be equal to its lower bound are presented. Sufficient conditions for the payoff at equilibrium to be equal to its upper bound are also presented.

Recent research has brought to light the vulnerability of deep neural networks (DNNs) to adversarial examples. While several methods have been proposed for generating physical adversarial examples, they often suffer from a critical flaw -conspicuous and easily detectable patterns by humans, limiting their real-world effectiveness. To overcome this limitation, we introduce an innovative approach termed "dual adversarial camouflage" (DAC) that generates natural adversarial camouflage in the physical world. Our DAC method leverages natural styles to hide attacks effectively. The process involves a two-stage training process. In the first stage, we learn the style features from style images. Building on this, the second stage optimizes the camouflage obtained in the first stage by minimizing the target detection score, thus significantly enhancing the attack performance. Experiment results show that the adversarial camouflage generated by our method has high naturalness and can effectively deceive object detectors. In practical tests, the attack success rate of our adversarial camouflage in both the digital and physical worlds is impressive, achieving 96.9% and 80% respectively. This showcases the real-world potential and robustness of our DAC method in evading detection.

The learning data requirements are analyzed for the construction of stealth attacks in state estimation. In particular, the training data set is used to compute a sample covariance matrix that results in a random matrix with a Wishart distribution. The ergodic attack performance is defined as the average attack performance obtained by taking the expectation with respect to the distribution of the training data set. The impact of the training data size on the ergodic attack performance is characterized by proposing an upper bound for the performance. Simulations on the IEEE 30-Bus test system show that the proposed bound is tight in practical settings.