Characterizing Evaluation Practices of Intrusion Detection Methods for Smartphones
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The appearance of a new Android platform and its popularity has resulted in a sharp rise in the number of reported vulnerabilities and consequently in the number of mobile threats. Mobile malware, a dominant threat for modern mobile devices, was almost non-existent before the official release of the Android platform in 2008. The rapid development of mobile platform apps and app markets coupled with the open nature of the Android platform triggered an explosive growth of specialized malware and subsequent search for effective defence mechanisms. In spite of considerable research efforts in this area, the majority of the proposed solutions have seen limited success, which has been attributed in the research community to the lack of proper datasets, lack of validation and other deficiencies of the experiments. We feel that many of these shortcomings are due to immaturity of the field and a lack of established and organized practice. To remedy the problem, we investigated the employed experimentation practices adopted by the smartphone security community through a review of 120 studies published during the period between 2008–2013. In this paper, we give an overview of the research in the field of intrusion detection techniques for the Android platform and explore the deficiencies of the existing experimentation practices. Based on our analysis we present a set of guidelines that could help researchers to avoid common pitfalls and improve the quality of their work.
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.
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 | 0.007 | 0.003 |
| 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 it