Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68043
Volume:
10 |
10 |
Oct 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Science and engineering
Jawaharlal Nehru New College Of Engineering
Computer Science and engineering
Jawaharlal Nehru New College Of Engineering
Computer Science and engineering
Jawaharlal Nehru New College Of Engineering
Computer Science and engineering
Jawaharlal Nehru New College Of Engineering
Computer Science and engineering
Jawaharlal Nehru New College Of Engineering
Remote technical interviews improve accessibility and reduce recruitment effort, but they also create integrity risks that are difficult to observe from the interview conversation alone. Candidates may be impersonated, receive assistance, leave the interview context, or use external resources not visible to the interviewer. InterviewShield proposes a modular multimodal framework combining computer-vision, audio, behavioral, and browser/system signals into an interpretable risk representation. Frame-level perception is separated from temporal behavior analysis, while a fusion layer aggregates heterogeneous evidence using confidence and time context. The candidate interface includes explicit consent and a pre-interview device check; the recruiter interface presents risk summaries and timestamped supporting evidence. Engineering targets include alert latency below two seconds, at least 80% module-level coverage, and at least 85% fusion-engine coverage. These remain targets rather than verified outcomes, and no numerical accuracy is claimed without a labeled validation set. Prototype testing establishes the modular workflow and identifies audio-analysis reliability as an open validation issue. InterviewShield is intended to support human review, not to make automated hiring or misconduct decisions.
KEYWORDS
InterviewShield presents a multimodal framework for supporting integrity in remote technical interviews. Its contribution is a structured architecture that combines visual, audio, temporal behavioral, and browser-level evidence into an interpretable risk representation rather than a claim of perfect automated fraud detection. The modular design supports independent development and testing, while the fusion layer provides confidence-aware aggregation and temporal context. The system is intended to help recruiters identify sessions or time intervals that deserve closer review; it is not intended to make irreversible hiring or misconduct decisions from a single model output. Consent, privacy safeguards, browser limitations, missing-signal handling, and an honest evaluation strategy provide a foundation for further empirical research and controlled validation.
[1] N. Gupta, A. Sharma, S. Shukla, and P. Kumar, “AI-based mock interview evaluator: An emotion and confidence classifier model,” International Journal of Research in Engineering and Innovation, vol. 9, no. 3, pp. 136–142, 2025, doi: 10.36037/IJREI.2025.9308. [2] N. S. Rai, A. K. R, A. P, and H. N. R, “AI Based Interview Evaluator: An Emotion and Confidence Classifier,” International Advanced Research Journal in Science, Engineering and Technology, vol. 11, no. 4, 2024, doi: 10.17148/IARJSET.2024.11442. [3] Y. Atoum, L. Chen, A. X. Liu, S. D. H. Hsu, and X. Liu, “Automated Online Exam Proctoring,” IEEE Transactions on Multimedia, vol. 19, no. 7, pp. 1609–1624, 2017, doi: 10.1109/TMM.2017.2656064. [4] A. C. Özgen, M. U. Öztürk, and U. Bayraktar, “Cheating Detection Pipeline for Online Interviews and Exams,” arXiv:2106.14483, 2021. [5] J. Xue, W. Wu, and Q. Cheng, “Intelligent invigilator system based on target detection,” Multimedia Tools and Applications, vol. 82, pp. 44673–44695, 2023, doi: 10.1007/s11042-023-15474-y. [6] A. K. Naveen, B. Singla, R. Wankhade, S. M., R. S., and R. M. R. Guddeti, “AutoOEP—A Multi-modal Framework for Online Exam Proctoring,” arXiv:2509.10887, 2025. [7] S. Mukherjee, V. Distler, G. Lenzini, and P. Cardoso-Leite, “Balancing the Perception of Cheating Detection, Privacy and Fairness: A Mixed-Methods Study of Visual Data Obfuscation in Remote Proctoring,” in Proceedings of the 2024 European Symposium on Usable Security (EuroUSEC 2024), pp. 337–353, 2024, doi: 10.1145/3688459.3688474. [8] B. Burgess, A. Ginsberg, E. W. Felten, and S. Cohney, “Watching the watchers: bias and vulnerability in remote proctoring software,” in 31st USENIX Security Symposium (USENIX Security 22), pp. 571–588, 2022.
Publication Date
10/16/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
6
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...