Novelty Detection for SilGeo Hardware Assurance
Bibliographic record
Abstract
In today's world, electronic hardware-level threats have become increasingly common. These threats can range from the infiltration of counterfeit or malicious hardware in the supply chain to the use of electronic attack tools. Due to the ever-evolving nature and customizability of inauthentic electronics, it is difficult to validate the authenticity of hardware. While measurement devices have been created to detect these threats, their successful deployment requires a high level of expertise. \n \nThis thesis addresses these challenges by proposing a novelty detection method for the \\gls{silgeo} hardware validation platform with low deployment barriers. It has been shown that this method can be trained on as few as three valid devices, and the entire training and application process is fully automated, requiring no expertise. The method incorporates Bayesian statistical models that rely on carefully selected assumptions and domain knowledge. Furthermore, maximum false positive rates can be estimated and adjusted without additional data. \n \nThe presented method is tested in several case studies on devices ranging from surface-mount integrated circuits to Wi-Fi-enabled disguised attack tools. In each case, the estimated maximum false positive rate exceeded the observed false positive rate, and most counterfeit and malicious devices were identified. This thesis presents a practical solution to detecting and validating hardware in a rapidly changing threat landscape.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 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".