Skip to content
Conference Open access

Research on Cybersecurity Risks and Protection Strategies Derived from Intelligent Algorithms

2026 · SHS Web of Conferences · 0 citations · 5 references

TL;DR

The study argues that, facing the constantly evolving attack patterns driven by intelligent algorithms, network security governance cannot rely solely on static rules and post-incident handling, and should further strengthen the capabilities of real-time threat identification, trusted identity verification, cross-entity collaborative response, and dynamic updates of security policies.

Abstract

While intelligent algorithms improve the efficiency of network system operation and maintenance, they also lower the technical threshold for malicious attacks, leading to new network threats exhibiting high concealment, automation, and precision. This study focuses on the network security risks derived from intelligent algorithms, deeply analyzing the evolution mechanisms of three core vulnerabilities: intelligent identity forgery, algorithm-driven vulnerability mining, and automated traffic attacks. The study points out that traditional feature-matching-based defense models lag significantly in dealing with such dynamic threats. Based on this, this paper proposes solutions from three dimensions: dynamic perception, proactive verification, and collaborative governance, aiming to build a more adaptive, interconnected, and forward-looking network security protection system. The study argues that, facing the constantly evolving attack patterns driven by intelligent algorithms, network security governance cannot rely solely on static rules and post-incident handling. Instead, it should further strengthen the capabilities of real-time threat identification, trusted identity verification, cross-entity collaborative response, and dynamic updates of security policies, thereby providing new practical references for the iterative upgrade of network security protection systems.

Read PDF

Similar papers

Open access Jul 2026

Advanced Machine Learning Model for Anticipating and Preventing Cyber Attacks Using Random Forest (RF)

An Advanced Machine Learning Model for Anticipating and Preventing Cyber Attacks Using Random Forest is presented, which effectively detects cyber threats with high accuracy and reliability, thereby improving threat anticipation and reducing security risks.

T Pushpalatha and RP Rajeshwari · 0 citations
Open access Jul 2026

Modern cybersecurity architecture for fraud prevention in administrative services

A cybersecurity architecture oriented toward fraud prevention in a service sector company in Lima, Peru, whose design is grounded in the documentary analysis of 385 technical incident records is proposed, forming a defense-in-depth capable of reducing residual exposure and sustaining a robust anti-fraud response in digitalized administrative environments.

Enrique Castellares Cuya, José Rengifo Espinal · 0 citations
Review Open access Jul 2026

AIS Cybersecurity: Challenges, Vulnerabilities, and Mitigation Strategies

This survey provides an AIS-first, security-focused synthesis of AIS cybersecurity research, bringing together cybersecurity, maritime operations, and data-science perspectives, that provides practical guidance for securing AIS-based systems and highlights open problems for future standardization and implementation.

Silvie Levy, Ehud Gudess, Danny Hendler · 0 citations
Conference Aug 2026

Improving Cybersecurity with Artificial Intelligence: Identification, Examination, and Mitigation of Cyber Threats

Cyberattacks are becoming more frequent and sophisticated in today’s digital world, rendering conventional security measures inadequate. In order to increase the accuracy of cyber threat detection, this study investigates the application of deeplearning methods to increase the accuracy of cyber threat detection. A cybersecurity dataset was used to test four classification models: Artificial Neural Networks (ANN), Random Forest, XGBoost, and Logistic Regression. The models were evaluated using the key 95.32. The performance of Artificial Neural Networks, Random Forest, XGBoost, and Logistic Regression was examined. These findings imply that learning-based and ensemble models are better at spotting intricate and changing attack patterns. In general, the study highlights the significance of clever, data-driven methods for creating cybersecurity defence systems that are quicker, more dependable, and more resilient.

D. Sharma, Inderdeep Kaur, Krishika Gupta et al. · 0 citations
Conference Jul 2026

Review of Cyber Threat Detection Techniques in Cloud Computing Environment

Cloud is the essential component for modern computer systems, offering businesses flexible scalability and on-demand resources. However, as attackers use more complex techniques to compromise cloud networks, this technological advancement has ushered in a new era of cybersecurity challenges. Wide-ranging effects, such as data loss, financial penalties, reputational harm, and legal responsibilities, can result from such breaches. In response to these challenges, a strong security framework is essential to effectively protect cloud infrastructure. Recently, several artificial intelligence (AI) techniques have been developed for cyber threat detection. Hence, to get deeper insight into this, the survey aims to analyse the role of cyber threat detection techniques and provide an overview of their applications. To achieve this, around 28 research papers from the years 2023-2026 are reviewed based on their methods, algorithms, datasets, performance metrics, and achievements. Furthermore, this work reviews different types of threats affecting the availability, confidentiality, and integrity of cloud services and resources, and examines the applications, including intrusion detection in cloud and several types of cyber threat detection systems. The core insights formulated in this review provide a comparison of analytics as well as future directions.

Pradnya Patil, J. Bakal · 0 citations
Review Aug 2026

An Analysis of Explainable Artificial Intelligence for Intelligent Cybersecurity Applications

The results show that XAI can improve the transparency, trustworthiness and effectiveness of AI-based cybersecurity systems, in addition to highlighting a range of privacy, adversarial robustness, scalability and evaluation challenges that warrant further research to ensure reliable deployment in the real world.

Raman Kumar · 0 citations