Strategi dan Efektivitas Deep Learning untuk Mitigasi Ancaman Keamanan Jaringan di Era IoT
Bibliographic record
Abstract
Pertumbuhan pesat perangkat Internet of Things (IoT) telah membuka peluang besar dalam transformasi digital di berbagai sektor, namun juga menghadirkan tantangan serius terkait keamanan jaringan. Perangkat IoT yang umumnya memiliki kapasitas komputasi terbatas menjadi sasaran empuk bagi berbagai jenis serangan siber. Penelitian ini bertujuan untuk mengevaluasi efektivitas berbagai pendekatan deep learning dalam mendeteksi ancaman keamanan pada jaringan IoT secara otomatis dan adaptif. Metode yang digunakan mencakup eksperimen komparatif terhadap beberapa arsitektur deep learning, seperti Transformer, CNN + LSTM, dan GAN + CNN, dengan memanfaatkan dataset publik UNSW-NB15. Penilaian performa dilakukan menggunakan metrik evaluasi seperti akurasi dan F1-score, serta analisis kemampuan model dalam mendeteksi serangan kompleks seperti DDoS, port scanning, dan serangan zero-day. Hasil penelitian menunjukkan bahwa model Transformer unggul dengan akurasi mencapai 99,1%, sementara model GAN + CNN menunjukkan keunggulan dalam mendeteksi pola serangan baru yang belum dikenali sebelumnya. Model CNN + LSTM juga terbukti efektif dalam menangkap pola spasio-temporal serangan. Penelitian ini memberikan kontribusi signifikan dalam pengembangan sistem deteksi intrusi cerdas berbasis deep learning untuk ekosistem IoT. Temuan ini berpotensi diterapkan pada sistem keamanan jaringan real-time dan berskala besar yang adaptif terhadap ancaman baru.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".