MétaCan
Menu
Back to cohort
Record W4405719083 · doi:10.18535/ijsrm/v08i4.ec03

Dynamic Adaptive API Security Framework Using AI-Powered Blockchain Consensus for Microservices

2020· article· en· W4405719083 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueInternational Journal of Scientific Research and Management (IJSRM) · 2020
Typearticle
Languageen
FieldComputer Science
TopicSoftware System Performance and Reliability
Canadian institutionsMarriott International (Canada)
Fundersnot available
KeywordsMicroservicesComputer scienceComputer securityBlockchainDenial-of-service attackByzantine fault toleranceApplication programming interfaceDistributed computingCloud computingWorld Wide WebFault toleranceThe InternetOperating system

Abstract

fetched live from OpenAlex

The concept of microservices architecture has nowadays become popular in the development of most software systems due to their benefits of application modularity and flexibility. Nevertheless, such architecture poses new security concerns especially on how to handle APIs that act as points of communication between different services. Traditional API protection strategies, based on predetermined patterns and a centralized platform, can be ineffective in guarding microservices because of the loosely connected structure of the latter. These limitations make APIs a sweet spot of highly skilled cyber threats like unauthorized data access, injection assaults, and Distributed Denial of Service (DDoS). This research presents a conceptual framework known as Dynamic Adaptive API Security Framework that uses Artificial Intelligence (AI) and blockchain technology to address these challenges. This first one uses AI to monitor API traffic and detect anomalies in real time with the help of the proposed framework. Through anomaly detection, machine learning models can detect unusual activity such as Suspicious usage patterns, patterns with malicious payloads, and pattern of many API calls. Also, AI offers an analytic feature, which can predict the vulnerability a certain target, based on data from previous attacks, and allow targeted prevention. Alongside AI, blockchain innovation is used to create an unalterable, distributed record of communication between API. Based on consensus mechanisms like Proof of Stake or Practical Byzantine Fault Tolerance, the framework guarantees the provenance of API transaction logs. These logs offer a great resource for the forensic activities in case of a breach of the system’s security. Also, smart contracts support even complex and constantly changing dynamic access control policies, adjusting as soon as AI-driven threat intelligence data is available. This synergy of using AI and blockchain in the framework generates an adaptable, transparent, and resilient security model that interfaces threats. Real-time anomaly detection together with immutable auditability integrated in the proposed framework improves the level of API security in microservices while simultaneously supporting GDPR and HIPAA compliance. This approach fills the gap in existing security solutions which cannot cope with the growing security issues in microservices format, providing a long-term solution for increasing security of complicated, decentralized microservices landscape. Summing up, this work presents a new comprehensive strategy to API security using the advantages of both AI and blockchain technologies. Applying the framework identifies how these technologies can be synchronously balanced and orchestrated to respond to threats, protect data input, and offer clear microservices security and foundation for the advancement of subsequent generation of software.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.786
Threshold uncertainty score0.956

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0020.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.064
GPT teacher head0.377
Teacher spread0.313 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it