Analyzing Adversarial Attacks Against Deep Learning for Intrusion\n Detection in IoT Networks
Bibliographic record
Abstract
Adversarial attacks have been widely studied in the field of computer vision\nbut their impact on network security applications remains an area of open\nresearch. As IoT, 5G and AI continue to converge to realize the promise of the\nfourth industrial revolution (Industry 4.0), security incidents and events on\nIoT networks have increased. Deep learning techniques are being applied to\ndetect and mitigate many of such security threats against IoT networks.\nFeedforward Neural Networks (FNN) have been widely used for classifying\nintrusion attacks in IoT networks. In this paper, we consider a variant of the\nFNN known as the Self-normalizing Neural Network (SNN) and compare its\nperformance with the FNN for classifying intrusion attacks in an IoT network.\nOur analysis is performed using the BoT-IoT dataset from the Cyber Range Lab of\nthe center of UNSW Canberra Cyber. In our experimental results, the FNN\noutperforms the SNN for intrusion detection in IoT networks based on multiple\nperformance metrics such as accuracy, precision, and recall as well as\nmulti-classification metrics such as Cohen's Kappa score. However, when tested\nfor adversarial robustness, the SNN demonstrates better resilience against the\nadversarial samples from the IoT dataset, presenting a promising future in the\nquest for safer and more secure deep learning in IoT networks.\n
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 | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".