Research on fault diagnosis and positioning of the distribution network (DN) has always been an important research direction related to power supply safety performance. The back propagation neural network (BPNN) is a commonly used intelligent algorithm for fault location research in the DN. To improve the accuracy of dual fault diagnosis in the DN, this study optimizes BPNN by combining the genetic algorithm (GA) and cloud theory. The two types of BPNN before and after optimization are used for single fault and dual fault diagnosis of the DN, respectively. The experimental results show that the optimized BPNN has certain effectiveness and stability. The optimized BPNN requires 25.65 ms of runtime and 365 simulation steps. And in diagnosis and positioning of dual faults, the optimized BPNN exhibits a higher fault diagnosis rate, with an accuracy of 89%. In comparison to ROC curves, the optimized BPNN has a larger area under the curve and its curve is smoother. The results confirm that the optimized BPNN has high efficiency and accuracy.

With the rapid development of big data, artificial intelligence, and Internet technologies, human–human contact and human–machine interaction have led to an explosion of voice data. Rapidly identifying the speaker’s identity and retrieving and managing their speech data among the massive amount of speech data have become major challenges for intelligent speech applications in the field of information security. This research proposes a vocal recognition technique based on information adversarial training for speaker identity recognition in massive audio and video data, as well as speaker identification when oriented to the information security domain. The experimental results show that the method projects data from different scene channels all onto the same space and dynamically generates interactive speaker representations. It solves the channel mismatch problem and effectively improves the recognition of the speaker’s voice patterns across channels and scenes. It is able to separate overlapping voices when multiple people speak at the same time and reduce speaker separation errors. It realizes speaker voice recognition for the information security field and achieves a recall rate of 89% in a large database, which is of practical value for the intelligent application field.

Federated learning has emerged as a promising paradigm for privacy-preserving multi-source data fusion. However, its distributed nature makes it vulnerable to poisoning attacks. Malicious clients inject poisoned noises into their local models, severely degrading the global model’s performance. While existing defense mechanisms attempt to mitigate these threats, they often overlook a critical vulnerability: historical knowledge can reveal clients’ training trajectories or data distributions, providing adversaries with new opportunities for attack. At the same time, the historical knowledge also serves as a tool for detecting and neutralizing malicious activities. In this paper, we address the challenge by proposing a novel attack method and a robust defense framework. First, we propose HisMSA, a stealthy, untargeted model poisoning attack based on historical information perception. HisMSA requires only a few compromised clients to significantly degrade global model accuracy while evading existing defenses. Second, we present DynHisFL, a versatile defense framework that enhances the global model’s robustness by identifying and filtering poisoned models through the analysis of divergence in historical model distributions, making it adaptable to various untargeted attacks. The experiment shows that with 10% malicious clients, the accuracy of HisMSA drops to 30%, approaching unavailability. Despite defenses like statistical feature analysis and topology distance detection, HisMSA still degrades performance by 5%-20%. DynHisFL improves accuracy by 71.3% even with a 20% attack ratio, while achieving an outstanding 98.7% poisoning detection accuracy. Ten model distribution metrics are evaluated, with Maximum Mean Discrepancy achieving a recall rate of 70%-100% across various poisoning strategies.

With the rapid development of big data, artificial intelligence, and Internet technologies, the human-human contact and human-machine interaction have produced an explosive growth of voice data. Rapidly identifying the speaker's identity and retrieving and managing his or her speech data in the massive amount of speech data has become a major challenge for intelligent speech applications in the field of information security. This research proposes a vocal recognition technique based on information adversarial training for speaker identity recognition in massive audio and video, and speaker identification when oriented to the information security domain. The experimental results show that the method projects data from different scene channels all onto the same space and dynamically generates interactive speaker representations. It solves the channel mismatch problem and effectively improves the recognition of speaker's voice patterns across channels and scenes. It is able to separate overlapping voices when multiple people speak at the same time and reduce speaker separation errors. It realizes speaker voice recognition for information security field and achieves 89% recall rate in massive database, which has practical application value for intelligent application field.