The ongoing digitalization enables stable control processes and smooth operations of Industrial Control Systems (ICSs). A direct consequence of the highly interconnected architecture of ICSs is the introduced cyber vulnerability and increasing cyber security threats to ICSs. Numerous researches pay attention to the security problem of ICSs. However, most current studies face two challenges. First, the interaction problem between the cyber layer and the physical layer of ICSs may result in incorrect attack response strategies. Second, ICSs are real-time systems, but existing defense decision algorithms based on game theory or reinforcement learning techniques have high computational complexity, which prevents them from making decisions quickly. In this paper, we design a new multi-attribute based method for quantifying rewards and propose a multi-attribute based Q-learning algorithm to resolve the interaction problem. In addition, to overcome the limitation of slow convergence, we develop an effective parallel Q-learning (PQL) algorithm to quickly find the optimal strategy. The experimental results show the effectiveness of the PQL algorithm. Compared with the Q-learning algorithm (QL) and the deep Q-network (DQN) algorithm, our proposed solution can reduce the average completion time by 12.5 to 37 percent.
10 October 2024 in IEEE Transactions on Services Computing
Cyber-physical systems (CPSs) are intricate systems integrating both physical and computational components. When these components fail due to malfunction or cyber-attack, potentially leading to significant damage or even collapse of the network topology. Cyber resilience, defined as the capability of a network to restore its function and structure after component failures, is crucial for ensuring that CPSs can sustain their operational capabilities in the face of complex disturbances. Recently, CPS resilience has garnered increasing attention, leading to the development of various resilience recovery methods. However, most existing studies address network and physical layer resilience in isolation, which hampers the ability to implement adaptive resilience recovery decisions across different systems. To overcome these limitations, we propose a multi-layered cascaded resilient recovery framework grounded in deep reinforcement learning. Initially, we synthesize the complex interactions between the information and physical layers in CPS resilience recovery from a global perspective, modeling the interrelations within CPSs. Subsequently, we introduce a hybrid resilient recovery strategy, encompassing both horizontal and vertical resilient recovery. The correlation matrix is used to partition the system into horizontal and vertical resilience slices. The resilient recovery strategy is subsequently modeled as an optimization problem using these slices. Following this, the Deep Recurrent Q-learning (DRQL) algorithm is introduced to implement the resilient recovery strategy in CPSs. While DRQL exhibits strong adaptability, it may lead to the sparse selection of critical samples, thereby hindering the learning process and convergence on essential experiences. To address this issue, we further develop the RR-DRQL algorithm, designed to identify the optimal CPS resilient recovery strategy. The RR-DRQL algorithm is rigorously proven to converge to the optimal solution through extensive theoretical analysis. Comprehensive experiments demonstrate that the RR-DRQL algorithm surpasses existing resilience recovery methods by 3.8%-25% regarding resilient policy recovery performance across realistic scenarios and various simulation platforms.
Pre-trained language models (PLMs) have significantly advanced natural language processing (NLP), establishing the "pre-training + fine-tuning" paradigm as a cornerstone approach in the field. However, the vast size and computational demands of Transformer-based PLMs present challenges, particularly regarding storage efficiency and processing speed. This paper addresses these limitations by proposing a novel lightweight PLM optimized for accurately understanding domain-specific computer terminology. Our method involves a pipeline parallelism algorithm designed to accelerate training. It is paired with an innovative mixed compression strategy that combines pruning and knowledge distillation to effectively reduce the model size while preserving its performance. The model is further fine-tuned using a dataset that mixes source and target languages to enhance its versatility. Comprehensive experimental evaluations demonstrate that the proposed approach successfully achieves a balance between model efficiency and performance, offering a scalable solution for NLP tasks involving specialized terminology.
Pretrained language models (PLMs) have significantly advanced natural language processing (NLP), establishing the "pretraining + fine-tuning" paradigm as a cornerstone approach in the field. However, the vast size and computational demands of transformer-based PLMs present challenges, particularly regarding storage efficiency and processing speed. This paper addresses these limitations by proposing a novel lightweight PLM optimized for accurately understanding domain-specific computer terminology. Our method involves a pipeline parallelism algorithm designed to accelerate training. It is paired with an innovative mixed compression strategy that combines pruning and knowledge distillation to effectively reduce the model size while preserving its performance. The model is further fine-tuned using a dataset that mixes source and target languages to enhance its versatility. Comprehensive experimental evaluations demonstrate that the proposed approach successfully achieves a balance between model efficiency and performance, offering a scalable solution for NLP tasks involving specialized terminology.
3 June 2026 in IEEE Transactions on Computational Social Systems
Cyber–physical–social systems (CPSSs) integrate the physical environment, information networks, and social interactions, serving as critical infrastructures in domains such as energy, transportation, and healthcare. While the multimodal and multilayered architecture of CPSS fosters innovation and operational efficiency, it simultaneously introduces significant security vulnerabilities. The high degree of interconnectivity inherent in CPSS makes them particularly susceptible to adversarial attacks, positioning them as high-risk targets. Developing effective attack strategies that leverage the unique data characteristics of CPSS, as well as establishing verifiable experimental frameworks, has become a prominent research focus. However, existing studies have not adequately addressed the development of robust attack models under limited data availability, resulting in problems such as unsatisfactory attack success rates, poor adversarial training, and insufficient attack stealth. To address these challenges, this article proposes a novel adversarial attack model, GC-GAN, which is based on generative adversarial networks (GANs). The GC-GAN framework comprises three core components: a generator, an authenticity discriminator, and an attack trainer. The generator employs the bipartite graph attribute-sharing theory and integrates graph and sequence encoders to extract latent patterns from known datasets. The discriminator and attack trainer are collaboratively trained to iteratively refine the generated samples by balancing authenticity with attack objectives. This collaborative mechanism enhances attack success rates while minimizing the risk of detection. Extensive experimental evaluations validate the efficacy of the proposed model. Compared to existing approaches, GC-GAN demonstrates significant improvements in both attack success rate and stealthiness.