SECURING LOW-POWER EDGE AI: A VULNERABILITY ANALYSIS AND CYBERSECURITY FRAMEWORK FOR RESOURCE-CONSTRAINED DEVICES
Bibliographic record
Abstract
The rapid deployment of Edge AI systems powered by low-power technology has creatednew operational challenges in healthcare facilities, autonomous vehicles, and industrial IoTdevices, leading to increased security vulnerabilities. Security mechanisms require strongcomputational power, which these efficiency and real-time-oriented systems do not possessby design. Predictable threats against Edge AI systems are now more prevalent due to theirlimited computing power. Security frameworks prove inefficient when used in Edge AIenvironments, creating a vital protection weakness. This research paper focuses on a newlightweight cybersecurity system designed for Edge AI systems that lack sufficient resources.The proposed security construct enables the deployment of effective cryptographic systemsand AI-based anomaly identification along with defence mechanisms suitable for real-timeedge devices operating with restricted power consumption. A realistic dataset, known as theCyber Threat Detection Dataset, was utilised to test the framework, which incorporatedmultiple normal and attack behaviours, as well as several different attack varieties. The highspeedintrusion detection system relies on Random Forest (RF), while a LightweightConvolutional Neural Network (CNN) handles anomaly detection activities within theframework, and Federated Learning (FL) decentralises learning across different edge nodeswith privacy protection. According to test results, the developed framework deliversadvanced threat detection accuracy, better energy efficiency, and faster inference speeds.Each security model partakes specific capabilities that enhance a layered defence, resulting ina protected, adaptable and scalable protection for Edge AI systems.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
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".