Yulong Zou

Yulong Zou, Bo Liu, Cun-Jing Zheng et al.

Leveraging multimodal information from Magnetic Resonance Imaging (MRI) plays a vital role in lesion segmentation, especially for brain tumors. However, in clinical practice, multimodal MRI data are often incomplete, making it challenging to fully utilize the available information. Therefore, maximizing the utilization of this incomplete multimodal information presents a crucial research challenge. We present a novel meta-guided multi-modal learning (MGML) framework that comprises two components: meta-parameterized adaptive modality fusion and consistency regularization module. The meta-parameterized adaptive modality fusion (Meta-AMF) enables the model to effectively integrate information from multiple modalities under varying input conditions. By generating adaptive soft-label supervision signals based on the available modalities, Meta-AMF explicitly promotes more coherent multimodal fusion. In addition, the consistency regularization module enhances segmentation performance and implicitly reinforces the robustness and generalization of the overall framework. Notably, our approach does not alter the original model architecture and can be conveniently integrated into the training pipeline for end-to-end model optimization. We conducted extensive experiments on the public BraTS2020 and BraTS2023 datasets. Compared to multiple state-of-the-art methods from previous years, our method achieved superior performance. On BraTS2020, for the average Dice scores across fifteen missing modality combinations, building upon the baseline, our method obtained scores of 87.55, 79.36, and 62.67 for the whole tumor (WT), the tumor core (TC), and the enhancing tumor (ET), respectively. We have made our source code publicly available at https://github.com/worldlikerr/MGML.

Liang Yu, Di Xie, Tao Jiang et al.

In this paper, we investigate the problem of minimizing the long-term total cost (i.e., the sum of energy cost and thermal discomfort cost) associated with a Heating, Ventilation, and Air Conditioning (HVAC) system of a multizone commercial building under smart grid environment. To be specific, we first formulate a stochastic program to minimize the time average expected total cost with the consideration of uncertainties in electricity price, outdoor temperature, the most comfortable temperature level, and external thermal disturbance. Due to the existence of temporally and spatially coupled constraints as well as unknown information about the future system parameters, it is very challenging to solve the formulated problem. To this end, we propose a realtime HVAC control algorithm based on the framework of Lyapunov optimization techniques without the need to predict any system parameters and know their stochastic information. The key idea of the proposed algorithm is to construct and stabilize virtual queues associated with indoor temperatures of all zones. Moreover, we provide a distributed implementation of the proposed realtime algorithm with the aim of protecting user privacy and enhancing algorithmic scalability. Extensive simulation results based on real-world traces show that the proposed algorithm could reduce energy cost effectively with small sacrifice in thermal comfort.

Liang Yu, Tao Jiang, Yulong Zou

In this paper, we investigate the problem of minimizing the sum of energy cost and thermal discomfort cost in a long-term time horizon for a sustainable smart home with a Heating, Ventilation, and Air Conditioning (HVAC) load. Specifically, we first formulate a stochastic program to minimize the time average expected total cost with the consideration of uncertainties in electricity price, outdoor temperature, renewable generation output, electrical demand, the most comfortable temperature level, and home occupancy state. Then, we propose an online energy management algorithm based on the framework of Lyapunov optimization techniques without the need to predict any system parameters. The key idea of the proposed algorithm is to construct and stabilize four queues associated with indoor temperature, electric vehicle charging, and energy storage. Moreover, we theoretically analyze the feasibility and performance guarantee of the proposed algorithm. Extensive simulations based on real-world traces show the effectiveness of the proposed algorithm.

Bo Liu, Yulong Zou, Jin Hong

In clinical practice, the robustness of deep learning models for multimodal brain tumor segmentation is severely compromised by incomplete MRI data. This vulnerability stems primarily from modality bias, where models exploit spurious correlations as shortcuts rather than learning true anatomical structures. Existing feature fusion methods fail to fundamentally eliminate this dependency. To address this, we propose CausalDisenSeg, a novel Structural Causal Model (SCM)-grounded framework that achieves robust segmentation via causality-guided disentanglement and counterfactual reasoning. We reframe the problem as isolating the anatomical Causal Factor from the stylistic Bias Factor. Our framework implements a three-stage causal intervention: (1) Explicit Causal Disentanglement: A Conditional Variational Autoencoder (CVAE) coupled with an HSIC constraint mathematically enforces statistical orthogonality between anatomical and style features. (2) Causal Representation Reinforcement: A Region Causality Module (RCM) explicitly grounds causal features in physical tumor regions. (3) Counterfactual Reasoning: A dual-adversarial strategy actively suppresses the residual Natural Direct Effect (NDE) of the bias, forcing its spatial attention to be mutually exclusive from the causal path. Extensive experiments on the BraTS 2020 dataset demonstrate that CausalDisenSeg significantly outperforms state-of-the-art methods in accuracy and consistency across severe missing-modality scenarios. Furthermore, cross-dataset evaluation on BraTS 2023 under the same protocol yields a state-of-the-art macro-average DSC of 84.49.

Yulong Zou, Jia Zhu, Xuelong Li et al.

This article examines the secrecy coding aided wireless communications from a source to a destination in the presence of an eavesdropper from a security-reliability tradeoff (SRT) perspective. Explicitly, the security is quantified in terms of the intercept probability experienced at the eavesdropper, while the outage probability encountered at the destination is used to measure the transmission reliability. We characterize the SRT of conventional direct transmission from the source to the destination and show that if the outage probability is increased, the intercept probability decreases, and vice versa. We first demonstrate that the employment of relay nodes for assisting the source-destination transmissions is capable of defending against eavesdropping, followed by quantifying the benefits of single-relay selection (SRS) as well as of multi-relay selection (MRS) schemes. More specifically, in the SRS scheme, only the single "best" relay is selected for forwarding the source signal to the destination, whereas the MRS scheme allows multiple relays to participate in this process. It is illustrated that both the SRS and MRS schemes achieve a better SRT than the conventional direct transmission, especially upon increasing the number of relays. Numerical results also show that as expected, the MRS outperforms the SRS in terms of its SRT. Additionally, we present some open challenges and future directions for the wireless relay aided physical-layer security.

Yulong Zou, Jia Zhu, Xianbin Wang et al.

This paper examines the security vulnerabilities and threats imposed by the inherent open nature of wireless communications and to devise efficient defense mechanisms for improving the wireless network security. We first summarize the security requirements of wireless networks, including their authenticity, confidentiality, integrity and availability issues. Next, a comprehensive overview of security attacks encountered in wireless networks is presented in view of the network protocol architecture, where the potential security threats are discussed at each protocol layer. We also provide a survey of the existing security protocols and algorithms that are adopted in the existing wireless network standards, such as the Bluetooth, Wi-Fi, WiMAX, and the long-term evolution (LTE) systems. Then, we discuss the state-of-the-art in physical-layer security, which is an emerging technique of securing the open communications environment against eavesdropping attacks at the physical layer. We also introduce the family of various jamming attacks and their counter-measures, including the constant jammer, intermittent jammer, reactive jammer, adaptive jammer and intelligent jammer. Additionally, we discuss the integration of physical-layer security into existing authentication and cryptography mechanisms for further securing wireless networks. Finally, some technical challenges which remain unresolved at the time of writing are summarized and the future trends in wireless security are discussed.

Linyuan Zhang, Guoru Ding, Qihui Wu et al.

The Byzantine attack in cooperative spectrum sensing (CSS), also known as the spectrum sensing data falsification (SSDF) attack in the literature, is one of the key adversaries to the success of cognitive radio networks (CRNs). In the past couple of years, the research on the Byzantine attack and defense strategies has gained worldwide increasing attention. In this paper, we provide a comprehensive survey and tutorial on the recent advances in the Byzantine attack and defense for CSS in CRNs. Specifically, we first briefly present the preliminaries of CSS for general readers, including signal detection techniques, hypothesis testing, and data fusion. Second, we analyze the spear and shield relation between Byzantine attack and defense from three aspects: the vulnerability of CSS to attack, the obstacles in CSS to defense, and the games between attack and defense. Then, we propose a taxonomy of the existing Byzantine attack behaviors and elaborate on the corresponding attack parameters, which determine where, who, how, and when to launch attacks. Next, from the perspectives of homogeneous or heterogeneous scenarios, we classify the existing defense algorithms, and provide an in-depth tutorial on the state-of-the-art Byzantine defense schemes, commonly known as robust or secure CSS in the literature. Furthermore, we highlight the unsolved research challenges and depict the future research directions.

Yulong Zou, Xianbin Wang, Weiming Shen et al.

Physical-layer security is emerging as a promising paradigm of securing wireless communications against eavesdropping between legitimate users, when the main link spanning from source to destination has better propagation conditions than the wiretap link from source to eavesdropper. In this paper, we identify and analyze the tradeoffs between the security and reliability of wireless communications in the presence of eavesdropping attacks. Typically, the reliability of the main link can be improved by increasing the source's transmit power (or decreasing its date rate) to reduce the outage probability, which unfortunately increases the risk that an eavesdropper succeeds in intercepting the source message through the wiretap link, since the outage probability of the wiretap link also decreases when a higher transmit power (or lower date rate) is used. We characterize the security-reliability tradeoffs (SRT) of conventional direct transmission from source to destination in the presence of an eavesdropper, where the security and reliability are quantified in terms of the intercept probability by an eavesdropper and the outage probability experienced at the destination, respectively. In order to improve the SRT, we then propose opportunistic relay selection (ORS) and quantify the attainable SRT improvement upon increasing the number of relays. It is shown that given the maximum tolerable intercept probability, the outage probability of our ORS scheme approaches zero for $N \to \infty$, where $N$ is the number of relays. Conversely, given the maximum tolerable outage probability, the intercept probability of our ORS scheme tends to zero for $N \to \infty$.