The rapid spread of misinformation on social media platforms escalates a serious threat to world socio-political stability, health and financial security. While current automated fake news detection models boast impressive accuracy scores, these are often due to memorisation of the training domain rather than genuine generalisation to unseen examples. This study tackles the pressing need for domain-robust misinformation and disinformation detection through the creation of a highly adaptive and deployable classification system. The challenge stems from the severe drop in performance when exposed to the domain shift, especially with the emergence of generative language models that can perform style-based attacks. The proposed solution employs a RoBERTa-base transformer model, fine-tuned on a large, multi-domain corpus of 37,143 instances. This dataset mixes the short, politically focused statements of the LIAR dataset with the long, multi-topic articles from the FakeNewsNet dataset and ensures cross-domain generalisation. Using full-parameter fine-tuning and evaluation across different domains, the model attained 86.7% accuracy, 87.3% macro precision and 86.4% macro F1-score on a diverse test corpus, surpassing traditional baselines. Importantly, the assessment unveiled a conservative labelling tendency with a 90.4% precision in detecting fake news and a 93.1% recall in detecting genuine news which prevents the severe consequences of mistakenly accusing legitimate news. Moreover, the design breaks out of research-only models with its integration into a real-time web service (based on Flask), providing sub-second inferences with confidence scores. This approach simultaneously addresses the problem of cross-domain vulnerability of state-of-the-art natural language processing models and demands deployable interpretability, setting a new benchmark for the implementation of natural language processing models in the fight against advanced, online misinformation.
The global Internet of Things (IoT) network has experienced unprecedented expansion, reaching 75.44 billion connected devices worldwide. Due to this rapid growth, the IoT ecosystem has become larger but also more vulnerable to various threats in cyberspace. As a result, this situation has accelerated the development of more complex cyberattacks, especially Distributed Denial of Service (DDoS) attacks, which can damage systems by overwhelming network traffic. This attack exploits the inherent vulnerabilities of IoT networks with limited resources, leading to significant service interruptions, monetary losses, and potentially the failure of vital infrastructures. As a result, this survey presents a new taxonomy of attack types, a thorough assessment of conventional and AI-driven detection techniques, and a comparison of advanced countermeasures. This survey aims to provide a comprehensive and systematic overview of DDoS attack detection, prevention, and mitigation approaches for the IoT. A major contribution of this work is the inclusion of blockchain-based security frameworks, federated learning, deep learning, machine learning, and quantum computing paradigms in its discussion for reducing DDoS attacks on the IoT. Furthermore, real-world case studies highlight the severe impact of such attacks on mission-critical domains, including smart cities, healthcare, and industrial control systems (ICSs). This survey provides a basis for cybersecurity researchers, security experts, and hobbyists, grounded in the understanding gained from previous research.
Integrating complementary information across distributed SPARQL end-points remains a significant challenge. While query federation enables access across multiple endpoints, constructing federated queries requires both SPARQL expertise and knowledge of the underlying ontological schemas. Current query rewriting techniques primarily focus on vocabulary translation to retrieve equivalent data, often overlooking the integration of complementary information spread across sources. To address these limitations, we propose an alignment-driven approach that assists users in constructing federated queries by leveraging ontology alignments. Our approach joins class paths – user-selected sequences of ontology classes and relationships – from source and target ontologies, guided by alignment-based filtering, into a unified path that serves as the foundation for generating federated SPARQL queries capturing complementary aspects of the user's intent. An experimental evaluation using OAEI Conference track datasets demonstrates that the generated queries consistently match reference queries in both structure and data retrieval across simple and complex mapping types, confirming the approach's effectiveness in integrating complementary data from heterogeneous sources.
To accurately identify and intercept harmful content generated in user interactions on Web platforms such as social media and online forums, this study proposes a Web interactive content filtering model that integrates Prompt classifiers and intent understanding. The model adopts a hierarchical review architecture with dual-module collaboration. The front-end deploys a Prompt classifier based on Deep Contrastive Learning (DCL), and uses the attention mechanism and deep convolutional network to perform rapid semantic analysis and preliminary screening of real-time comments and conversations. The back-end introduces an intent understanding module based on search-enhanced generation and Large Language Models (LLMs) to conduct in-depth contextual analysis of preliminary screening warning content to distinguish malicious attacks from legitimate sensitive topic discussions. Experiments showed that the system performed well on a test set containing 52,397 Chinese Web interactive texts. The Prompt classifier module achieved a precision of 95.2% and a recall of 96.5%. After collaborative calibration with the intent understanding module, the false alarm rate of the system was significantly reduced to 4.4%, while the recall rate remained at 96.1%. From the results, this study provides a content security solution for Web interactive scenarios that combines high accuracy, strong semantic understanding capabilities, and real-time response performance. It can effectively purify the cyberspace environment while ensuring freedom of interaction, with important practical application value.
Play-to-Earn (P2E) game economies integrated with Automated Market Maker (AMM) protocols face persistent sustainability challenges driven by whale-induced price volatility and the absence of effective token-burning mechanisms. These issues erode economic fairness and discourage long-term participation within web-based blockchain gaming platforms. This paper proposes EG-AMM (Epoch-Guarded Automated Market Maker), a software engineering framework that adds a governance-aware volatility protection layer to existing AMM-based P2E infrastructures without modifying the underlying pricing model. Inspired by circuit breaker mechanisms in traditional finance, EG-AMM enforces per-epoch dynamic swap allowances for individual players, computed from price impact tolerance and configurable through Decentralized Autonomous Organization (DAO) parameters. The framework employs Merkle-proof-based cryptographic verification and on-chain accounting to ensure allowance limits are transparent and tamper-resistant. Unlike existing pool-level approaches such as static transaction caps or dynamic fee schedules, EG-AMM operates at the individual player level, curbing whale dominance while preserving equitable market access for ordinary players and newcomers. Preliminary analysis and game-theoretic simulation confirm improvements in price stability, participation fairness, and economic resilience, offering a practical and deployable path toward sustainable token ecosystems in blockchain-integrated gaming applications.
