Flexible Intrusion Detection Systems for Memory-Constrained Embedded Systems
Bibliographic record
Abstract
Embedded systems are widely used in critical situations and hence, are targets for malicious users. Researchers have demonstrated successful attacks against embedded systems used in power grids, modern cars, and medical devices. This makes building Intrusion Detection Systems (IDS)for embedded devices a necessity. However, embedded devices have constraints(such as limited memory capacity) that make building IDSes monitoring all their security properties challenging. In this paper, we formulate building IDS for embedded systems as an optimization problem. Having the set of the security properties of the system and the invariants that verify those properties, we build an IDS that maximizes the coverage for the security properties, with respect to the available memory. This allows our IDS to be applicable to a wide range of embedded devices with different memory capacities. In our formulation users may define their own coverage criteria for the security properties. We also propose two coverage criteria and build IDSes based on them. We implement our IDSes for SegMeter, an open source smart meter. Our results show that our IDSes provide a high detection rate in spite of memory constraints of the system. Further, the detection rate of our IDSes at runtime are close to their estimated coverage at design time. This validates our approach in quantifying the coverage of our IDSes and optimizing them.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".