Intrusion Detection System for Embedded Systems
Bibliographic record
Abstract
Embedded devices are widely used in modern life. Smart meters are installed at homes, measure electricity consumption, and provide a two-way communication with the utility server. Modern cars consist of tens of Electronic Control Units (ECU) that control different components of the car such as speed, door locks, and breaks. Medical devices such as pacemakers and insulin pumps are implanted in the bodies of patients, and control their heart rate and insulin level. These devices are performing critical tasks and hence, their security is important. However, in recent years, researchers have found vulnerabilities in all these classes of devices, and have successfully demonstrated attacks against them. Given the critical nature of use cases of embedded systems, building Intrusion Detection System (IDS) for them is a necessity. However, embedded systems have constraints that make building IDS for them challenging. One of these constraints is memory. Memory capacity of embedded devices may be as small as several hundreds of kilobytes. This makes traditional solutions for building IDSes unusable. In my research, we analyze the security of embedded devices. Based on the results of my analysis, we develop techniques to automatically build IDSes for embedded devices, within their memory capacity, while optimizing the detection rate of the IDS with respect to the user's criteria. This research, makes developing IDSes for different classes of embedded systems, and with different memory capacities easier, and improves their security.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
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".