Securing Email Archives through User Modeling
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
Online email archives are an under-protected yet extremely sensitive information resource. Email archives can store years worth of personal and business email in an easy-to-access form, one that is much easier to compromise than messages being transmitted "on the wire." Most email archives, however, are protected by reusable passwords that are often weak and can be easily compromised. To protect such archives, we propose a novel user-specific design for an anomaly-based email archive intrusion detection system. As a first step towards building such a system, we have developed a simple probabilistic model of user email behavior that correlates email senders and a user's disposition of emails. In tests using data gathered from three months of observed user behavior and synthetic models of attacker behavior, this model exhibits a low rate of false positives (generally one false alarm every few weeks) while still detecting most attacks. These results suggest that anomaly detection is a feasible strategy for securing email archives, one that does not require changes in user authentication or access behavior.
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 | 0.000 | 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 | 0.000 |
| 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