Cryptographic Techniques in Artificial Intelligence Security: A Bibliometric Review
Bibliographic record
Abstract
With the rise in applications of artificial intelligence (AI) across various sectors, security concerns have become paramount. Traditional AI systems often lack robust security measures, making them vulnerable to adversarial attacks, data breaches, and privacy violations. Cryptography has emerged as a crucial component in enhancing AI security by ensuring data confidentiality, authentication, and integrity. This paper presents a comprehensive bibliometric review to understand the intersection between cryptography, AI, and security. A total of 495 journal articles and reviews were identified using Scopus as the primary database. The results indicate a sharp increase in research interest between 2020 and January 2025, with a significant rise in publications in 2023 and 2024. The key application areas include computer science, engineering, and materials science. Key cryptographic techniques such as homomorphic encryption, secure multiparty computation, and quantum cryptography have gained prominence in AI security. Blockchain has also emerged as an essential technology for securing AI-driven applications, particularly in data integrity and secure transactions. This paper highlights the crucial role of cryptography in safeguarding AI systems and provides future research directions to strengthen AI security through advanced cryptographic solutions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.040 | 0.059 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".