The rapid advancement of Large Language Models (LLMs) has driven significant progress in Natural Language Interface to Database (NLIDB). However, the widespread adoption of LLMs has raised critical privacy and security concerns. During interactions, LLMs may unintentionally expose confidential database contents or be manipulated by attackers to exfiltrate data through seemingly benign queries. While current efforts typically rely on rule-based heuristics or LLM agents to mitigate this leakage risk, these methods still struggle with complex inference-based attacks, suffer from high false positive rates, and often compromise the reliability of SQL queries. To address these challenges, we propose SafeNLIDB, a novel privacy-security alignment framework for LLM-based NLIDB. The framework features an automated pipeline that generates hybrid chain-of-thought interaction data from scratch, seamlessly combining explicit security reasoning with SQL generation. Additionally, we introduce reasoning warm-up and alternating preference optimization to overcome the multi-preference oscillations of Direct Preference Optimization (DPO), enabling LLMs to produce security-aware SQL through fine-grained reasoning without the need for human-annotated preference data. Extensive experiments demonstrate that our method outperforms both larger-scale LLMs and ideal-setting baselines, achieving significant security improvements while preserving high utility.

Aiming at the state master-slave synchronization problem of discrete-time output-coupled neural networks (OCNNs), this study proposes a novel control framework. Deviating from the existing studies, this study aims at the constraint that the output state cannot obtain all neuron state information, innovatively constructs full-dimensional observers in the master/slave system respectively to realize state reconstruction, which solves the problem of missing reference trajectory caused by incomplete state information of the master system, and realizes state synchronization for the first time under the output-coupled framework. A round-robin (RR) protocol is introduced to dynamically schedule the output-coupled communication among neurons to address the transmission efficiency bottleneck under limited bandwidth resources. To allocate communication resources more intelligently, a novel event-triggered (ET) mechanism is designed. Under this mechanism, the triggering threshold is constructed based on the last triggering instant and is updated according to the most current triggering instant. It significantly reduces overall resource consumption while ensuring control performance. Then, the joint Lyapunov function is constructed based on the designed observer-controller-protocol interaction dynamic model. It derived a quantitative relationship between the triggering frequency and the error decay boundary, thereby providing a quantifiable basis for precision tuning in network control. Finally, the effectiveness of the proposed method is verified by circuit simulation.

The study investigates the problem of attack-compensated control for two-dimensional (2-D) fuzzy systems modeled by the Roesser framework, subject to the constraints of limited communication channels. A novel event-triggered stochastic protocol (ETSP) with nonhomogeneous sojourn probabilities is introduced to save communication resources. By randomly selecting a controller node at each time step to transmit signals, the protocol schedules communication between controllers and actuators, thereby reducing communication load. To address the injection of false data into control signals caused by network attacks, a compensation mechanism based on a sojourn-probability-based predictor is designed. Sufficient conditions are subsequently established, based on Lyapunov theory, to ensure the mean-square asymptotic stability of the closed-loop system while preserving the desired performance level. Finally, the particle swarm optimization (PSO) algorithm is employed to enhance the controller design, and a simulation example is provided to verify the effectiveness and applicability of the proposed method.

This paper investigates the fuzzy censoring control problem for two-dimensional (2-D) discrete fuzzy systems characterized by the Roesser model. A novel event-triggered random protocol based on nonhomogeneous sojourn probability is proposed to effectively alleviate communication loads in 2-D fuzzy systems. To address signal fading effects, a censoring strategy is introduced to quantify the severity of signal degradation in transmitted data. The censored control input is subsequently modeled through a Tobit framework, thereby facilitating the design of an integrated state feedback control scheme for 2-D fuzzy systems. By leveraging Lyapunov stability theory, sufficient conditions are derived to guarantee the asymptotic mean-square stability of the closed-loop system while satisfying prescribed performance specifications. Furthermore, parameters are optimized via genetic algorithms to mitigate redundant conservatism associated with linear matrix inequalities. Finally, a gas absorption, water stream heating and air drying industrial case are carried out to verify the theoretical rigor and practical effectiveness of the proposed methodology.

This paper delves into the output feedback sliding mode control (SMC) problems in a class of Interval Type-2 (IT2) fuzzy systems affected by sensor faults. Firstly, a Markovian chain is employed to depict transmission channels vulnerable to stochastic deception attacks, providing a more accurate representation of the real-world scenario. Secondly, by leveraging historical estimates of fault signals, a novel learning-based observer integrated with a Saturation Function is proposed to reconstruct sensor faults. This observer incorporates a dynamic saturation level aimed at enhancing filtering performance. Subsequently, based on the estimated fault information, an output feedback SMC law is designed, and its finite-time boundedness is analyzed. Finally, the proposed approach and its associated theoretical findings are extended to an inverted pendulum model.

This study investigates an asynchronous sliding-mode control (SMC) strategy tailored for interval type-2 (IT2) fuzzy switching systems, specifically addressing challenges posed by cyber-attacks. Distinct from existing stochastic switching strategies, a novel duration-time-based switching rule is proposed that integrates both sojourn probability and mode duration, significantly reducing computational complexity and aligning more closely with practical requirements. To mitigate mode-switching-induced chattering and enhance robustness against uncertainties and disturbances, an innovative fuzzy SMC law with a learning mechanism is developed. Notably, a recursive sliding-mode learning controller is introduced, replacing abrupt switching actions with iterative learning adjustments to progressively guide system states onto the sliding surface, thereby significantly improving control smoothness and reducing chattering. To effectively handle cyber-attacks disrupting mode transmission, a comprehensive mismatched model that dynamically synchronizes the modes of the system and the controller is introduced, offering improved resilience compared to traditional fixed mismatch approaches. Utilizing the proposed learning-based SMC and Lyapunov stability theory, sufficient conditions ensuring mean-square stability of the system are derived. Finally, the practical effectiveness and distinct superiority of the proposed methods are demonstrated through simulations using mass-spring-damper and tunnel diode circuit models.

This article investigates the discrete-time fuzzy complex networks (FCNs) event-triggered (ET) synchronization control problem by considering the coupling effect and cyber attacks. To prevent data conflicts caused by communication resource limitations, a round-robin (RR) protocol is introduced to regulate the communication transmission order among coupled nodes. To be more general and flexible against Denial-of-Service (DoS) attacks, the concept of average dwelling time ratio (ADTR) is proposed to evaluate DoS attack models. In addition, a DoS-attack-aware ET mechanism is developed. Under this mechanism, a threshold parameter is dynamically adjusted according to the active and dormant time of the DoS attacks. The correlated co-design of anti-attack security control and ET mechanism is realized. Compared with the existing results, the scheme improves the control performance while reducing the controller update frequency. Then, by establishing appropriate Lyapunov function, sufficient criteria for synchronization of discrete-time FCNs are obtained, and a controllable range of the ADTR is calculated. Finally, the effectiveness of the proposed DoS-attack-aware ET control scheme based on RR protocol is verified through two simulations.

In this study, the synchronization problem of discrete-time fuzzy complex networks (FCNs) is investigated based on a state-dependent intermittent memory-event-triggered (MET) scheme. To alleviate the burden of network communication, a state-dependent-region-partitioning-based intermittent mechanism is proposed to set the working/rest interval of the controller. Compared with the existing results, it realizes on-demand control, reduces resource consumption, and expands applicability. A MET mechanism that depends on historical triggering states is developed during the working interval, which adds “smarter” to the triggering decision. Besides, a working-state-dependent threshold function is designed in the triggering condition, which realizes the correlation between intermittent and event-triggered mechanisms. Compared with the existing results, the mechanism provides intelligent regulation of the triggering instant, thereby optimizing the controller update instant and control effect, achieving the goal of improving the control effect while reducing the triggering frequency. Sufficient criteria for achieving synchronization of discrete-time FCNs are derived using Lyapunov stability theory under the state-dependent intermittent MET scheme. Simulation results are presented to demonstrate the effectiveness of the proposed scheme.

This article focuses on addressing the asynchronous filtering problem in T-S fuzzy sampled-data systems under the presence of censored measurements and non-uniform sampling. In contrast to existing approaches that rely on Markov processes to govern nonuniform sampling, a sojourn probability strategy is adopted to capture the random behavior of sampling periods. This strategy provides easily measurable information, surpassing the complexities associated with obtaining transition probabilities. Moreover, the variations in nonhomogeneous sojourn probability are controlled by a deterministic switching signal, enabling wider applicability compared to existing methods. The fading degree of transmitted data are assessed through a censoring strategy, and the measurement is modeled using a Tobit model. Considering the presence of nonuniform sampling periods and asynchronous premise variables, a general asynchronous fuzzy filtering method is carried out, and sufficient conditions are derived to ensure the mean-square stability of the resulting system. Finally, the developed methodology is validated through a numerical example, showcasing its applicability and effectiveness.

This study is concerned with protocol-based asynchronous filtering for interval type-2 (IT2) fuzzy systems subject to time-varying saturation functions. Two mutually independent Markov processes are proposed to characterize the random manners of intermittently failure and transmission sequence of sensor nodes, and a new joint Markov process is formulated by adopting the merging technique. Aiming at curbing the data collision and improving network utilization in the restricted network, an ETRP is implemented to govern whether to orchestrate the packets and which one to be launched simultaneously. A novel asynchronous filter is formulated under the constraint of saturation with the hope to improve filtering performance. This construction involves the dynamic adaptation of the saturation level in tandem with the estimation error. Additionally, the mismatched modes between the newly joined Markov process and filter are characterized by a hidden Markov model. Eventually, two examples are applied to verify the availability of the theoretical results.