Existing machine learning and deep learning approaches

The gap

Evidence profile

Sourced from the stated research gap and future work and inline gaps of the source papers, classified as general, drawn from work published between 2024 and 2026, spanning 2 journals. Those papers have been cited 129 times in total.

Supporting evidence — 3 representative gaps

• An adaptive neuro-fuzzy blockchain–AI framework for secure and intelligent FinTech transactions (2026) · Scientific Reports · doi

  Existing machine learning and deep learning approaches provide high detection accuracy but rely on centralized architectures and exhibit limited adaptability to evolving fraud patterns. Blockchain-based solutions improve transaction integrity and auditability but generally lack intelligent, real-time threat detection and adaptive risk assessment capabilities.

  generalstated research gap
  Keywords: existing machine learning deep approaches provide high detection
• Blockchain-Integrated AI Cybersecurity Framework for Deepfake Detection and Secure Digital Identity Verification (2026) · Zenodo (CERN European Organization for Nuclear Research) · doi

  This research presents a novel framework that integrates Artificial Intelligence and Blockchain technologies to address the challenges of deepfake detection and digital identity verification. The proposed system leverages the strengths of CNN and LSTM models to analyze multimedia content and detect inconsistencies, while the TrustScore mechanism enhances the interpretability of the results. The use of blockchain ensures that the verification data is stored in a secure and immutable manner, providing transparency and trust. The results of our experiment show that the system is really accurate and does well in many different tests. By using federated learning, we can make the system even better at handling lots of data and keeping information private, which makes it a good choice for using in the real world. This research helps us create online systems that are safe and trustworthy by giving us a complete solution that combines smart detection with secure verification. It's like having a strong shield that protects our digital world from harm. The system is designed to be flexible and can work well in many different situations, which is important for making sure it can be used in lots of different ways. Overall, our research is an important step towards creating a safer and more trustworthy digital world, and we're excited to see how it can be used in the future. Future work will focus on improving the efficiency of the system, reducing computational costs, and extending the framework to support real-time streaming applications. Additionally, efforts will be made to enhance the robustness of the model against adversarial attacks and to explore the use of advanced blockchain technologies for improved scalability. Overall, the proposed framework represents a significant step forward in the field of cybersecurity and digital identity verification. Our tests have proven that our system makes a big difference in how accurately it detects things and how reliable it is. Using blockchain technology stops people from messing with the data, and adding AI means the system can keep learning and getting better at finding new threats. So, we can trust that the system will work well and quickly spot any potential problems. By combining blockchain and AI, we've made the system more trustworthy and better at detecting issues. This means we can have faith in its performance and know it will keep getting better over time.

  generalfuture workevidence 5/5
  Keywords: system blockchain digital verification better framework well different using world trustworthy technologies detection identity proposed
• Blockchain security enhancement: an approach towards hybrid consensus algorithms and machine learning techniques (2024) · Scientific Reports · cited 129× · doi

  • Future research should focus on self-learning systems, which have the potential to hybrid consensus mecha- nisms. com/scientificreports/Open issues and challenges of the hybrid consensus approach Open issues of the proposed research approach Integrating ML, deep learning, and RL with blockchain protocols can improve security, performance, and deci- sion-making capabilities. However, it also presents open issues and challenges that researchers and practition- ers must consider carefully. Blockchain for deep learning: Review and open challenges. A survey on blockchain solutions in DDoS attacks mitigation: Techniques, open challenges and future directions. Reinforcement learning in blockchain-enabled IIoT networks: A survey of recent advances and open challenges.

  generalinline gapsevidence 5/5
  Keywords: open challenges learning blockchain issues future hybrid consensus approach deep survey focus self systems potential

Questions about this gap