Open research questions in Spam and Phishing Detection

What the literature leaves open

• While numerous studies have attempted to apply Cialdini’s principles of influence—reciprocity, commitment, social proof, authority, liking, and scarcity—to phishing detection, the synergistic effect of combining these principles within detection models remains unexplored.

  The synergy of influence: a unified framework for phishing email detection using persuasion principle interactions · 2026 · DOI

• Future research should focus on additional factors influencing vulnerability and the effectiveness of various intervention strategies.

  Unveiling deception: a socio-economic analysis of smishing attacks on mobile money transaction users · 2025 · DOI

• However, the study acknowledges limitations in its reliance on base models and emphasizes the need for further research on fine-tuning and parameter optimization.

  Benchmarking and Evaluating Large Language Models in Phishing Detection for Small and Midsize Enterprises: A Comprehensive Analysis · 2025 · DOI

• This study focuses on two under-researched factors influencing young adults’ susceptibility to social media phishing: the user’s relation to the message sender and Fear of Missing Out (FoMO).

  Friend or phisher: how known senders and fear of missing out affect young adults' phishing susceptibility on social media · 2024 · DOI

• The study suggests that future research should focus on improving the accuracy and reliability of spam detection systems. The study suggests that future research should explore the use of other machine learning algorithms and techniques for spam detection. The study suggests that future research should investigate the application of spam detection systems to other domains.

  Comparative Study of Machine Learning Algorithms for E-mail Spam Detection · 2026 · DOI

• The study identifies a research gap in the development of effective spam detection systems that can generalize to unseen data. The study notes that traditional rule-based filters have been replaced by statistical and machine learning techniques, but there is still a need for more accurate and reliable spam detection systems.

  Comparative Study of Machine Learning Algorithms for E-mail Spam Detection · 2026 · DOI

• Utilizing deep learning and transformer-based models to improve the detection accuracy. Integrating behavioral and metadata features like reviewer activity history and temporal patterns.

  Fake Online Product Review Detection Using Supervised and Semi-Supervised Opinion Mining · 2026 · DOI

• The web-based implementation uses Flask/Streamlit, but the paper does not address how the framework integrates with existing security infrastructure (email gateways, browser extensions, corporate proxies) or handles browser-based QR scanning with varying camera quality and lighting conditions.

  Unified URL and QR Based Phishing Detection Framework · 2026 · DOI

• While ethical considerations address data protection and transparency, the paper does not evaluate adversarial robustness: how the model performs against evasion attacks (e.g., homograph attacks, obfuscated URLs, dynamically generated QR codes with steganographic encoding).

  Unified URL and QR Based Phishing Detection Framework · 2026 · DOI

• Low accuracy of traditional methods for detecting fake reviews. Scalability issues of traditional methods for detecting fake reviews. Limited feature analysis of traditional methods for detecting fake reviews.

  Aspect-Based Deep Learning Model for Spam Review Detection · 2026 · DOI

• The existing systems for detecting fake reviews face several limitations, including low accuracy and scalability issues. The proposed system aims to address these limitations using machine learning and natural language processing techniques.

  Aspect-Based Deep Learning Model for Spam Review Detection · 2026 · DOI

• Integrating the system with browser extensions or network monitoring tools. Expanding the dataset to include more types of malicious URLs. Improving the performance of the system using other machine learning models.

  Malicious URL Detection Using Machine Learning · 2026 · DOI

• Traditional security mechanisms are reactive and often fail to detect new threats. There is a need for a system that can detect malicious URLs in real-time.

  Malicious URL Detection Using Machine Learning · 2026 · DOI

• Current detection methods are ineffective against new and unknown phishing attacks. Traditional phishing detection techniques are insufficient for real-time and extensive protection.

  Improved Machine Learning-Based Model for Phishing Website and URL Detection · 2026 · DOI

• The lack of a regulatory framework and centralized internet surveillance exposes users to security threats. Phishing detection methods face significant constraints related to data privacy, scalability, and the rapid emergence of novel attack patterns.

  Phishing in the age of distributed intelligence: taxonomies, detection strategies, and the emerging role of federated learning · 2026 · DOI

• The lack of a comprehensive survey on phishing taxonomies, detection strategies, and the role of Federated Learning. The need for a unified, multidimensional taxonomy for categorizing phishing attacks.

  Phishing in the age of distributed intelligence: taxonomies, detection strategies, and the emerging role of federated learning · 2026 · DOI

• Future research can focus on improving the performance of BiGRU and BiLSTM models. Future research can explore the application of other deep learning models to phishing URL detection.

  A comparative deep Learning approach for phishing URL detection · 2026 · DOI

• Traditional machine learning methods are not as effective as deep learning methods for phishing URL detection. There is a need for more effective phishing detection systems.

  A comparative deep Learning approach for phishing URL detection · 2026 · DOI

• Traditional rule-based detection systems are no longer effective against dynamically evolving phishing techniques. The rapid digitalization of banking, e-commerce, social networking, and government services has significantly increased reliance on web platforms while simultaneously expanding cybersecurity threats.

  AI-Powered Detection of Fraudulent Web Platforms Using Behavioral and Structural Analysis · 2026 · DOI

• Future research should investigate aspect-level analysis and combinational approaches to enhance the accuracy and reliability of fake review detection. Future research should explore the use of other machine learning approaches and imbalanced data handling techniques. Future research should consider the development of more effective fake review detection systems.

  Research Trends on Sentiment Analysis and Imbalanced Data Handling in Fake Review Detection: A Systematic Literature Review · 2026 · DOI

• There is a paucity of comprehensive research addressing fake review detection through sentiment analysis and imbalanced data handling. Most studies focus on sentiment analysis at the document level, with limited attention given to aspect-level analysis. There is a need for more research on combinational approaches to enhance the accuracy and reliability of fake review detection.

  Research Trends on Sentiment Analysis and Imbalanced Data Handling in Fake Review Detection: A Systematic Literature Review · 2026 · DOI

• Traditional detection systems exhibit low accuracy when dealing with complex and evolving fraud patterns. They suffer from high rates of false positives and false negatives. The proposed system can be further improved by incorporating advanced deep learning and artificial intelligence techniques.

  Online Recruitment Fraud (ORF) Detection Using Deep Learning Approaches · 2026 · DOI

• Integrating transformer-based models such as BERT or GPT-based architectures. Incorporating real-time monitoring systems that continuously analyze newly posted job advertisements. Expanding the system to include multi-modal data analysis.

  Online Recruitment Fraud (ORF) Detection Using Deep Learning Approaches · 2026 · DOI

• Malicious URLs are constantly evolving. URL threat classification is a challenging task. There is a need for a framework that can handle the complexity of URL threat classification.

  A Hybrid Ensemble–Instance Learning Framework for Malicious URL Detection Using XGBoost and Adaptive KNN · 2026 · DOI

• Past studies have been constrained in ensemble and instance-based paradigms in URL threat classification. There is a need for a hybrid framework that combines the strengths of both paradigms.

  A Hybrid Ensemble–Instance Learning Framework for Malicious URL Detection Using XGBoost and Adaptive KNN · 2026 · DOI

Most-cited papers in Spam and Phishing Detection

• Social phishing · Communications of the ACM · 2007 · 792 citations
• The state of phishing attacks · Communications of the ACM · 2011 · 385 citations
• Fame for sale: Efficient detection of fake Twitter followers · Decision Support Systems · 2015 · 374 citations
• Why do people get phished? Testing individual differences in phishing vulnerability within an integrated, information processing model · Decision Support Systems · 2011 · 336 citations
• Who Are the Phishers? Phishing Scam Detection on Ethereum via Network Embedding · IEEE Transactions on Systems, Man, and Cybernetics: Systems · 2022 · 334 citations
• Fake online reviews: Literature review, synthesis, and directions for future research · Decision Support Systems · 2020 · 293 citations
• Phishing environments, techniques, and countermeasures: A survey · Computers & Security · 2017 · 251 citations
• Security awareness of computer users: A phishing threat avoidance perspective · Computers in Human Behavior · 2014 · 239 citations
• Phishing Detection System Through Hybrid Machine Learning Based on URL · IEEE Access · 2023 · 229 citations
• A Deep Learning-Based Phishing Detection System Using CNN, LSTM, and LSTM-CNN · Electronics · 2023 · 221 citations

Most recent work

• An Efficient Feature Selection Technique to Enhance Spam Email Detection · TEM Journal · 2026
• AI-generated fake review detection · Decision Support Systems · 2026
• Domains of deception: phishing through the lens of ownership · Computers & Security · 2026
• Comparative Evaluation of Machine Learning Models for Phishing Website Detection Using URL-Based Features · IEEE Communications Standards Magazine · 2026
• On bot-proofing · Assessment & Evaluation in Higher Education · 2026
• DETECTION OF INVALID CLICKS IN DIGITAL ADVERTISING USING ARTIFICIAL INTELLIGENCE TECHNIQUES · JDEBM · 2026
• Comparative Study of Machine Learning Algorithms for E-mail Spam Detection · International Journal of Mathematics And Computer Research · 2026
• Real-Time Phishing URL Detection Pipeline in the PHISHRADOR System · International Scientific Journal of Engineering and Management · 2026
• Deep learning-based phishing classification framework for accurate detection using optimized URL intelligence · Scientific Reports · 2026
• Machine Learning-Based Phishing URL Detection System Using Feature Engineering and Classification Models · International Journal of Creative and Open Research in Engineering and Management · 2026

Related topics in Computer Science