A Large-Scale Analysis of the Semantic Password Model and Linguistic Patterns in Passwords
Bibliographic record
Abstract
In this article, we present a thorough evaluation of semantic password grammars. We report multifactorial experiments that test the impact of sample size, probability smoothing, and linguistic information on password cracking. The semantic grammars are compared with state-of-the-art probabilistic context-free grammar ( PCFG ) and neural network models, and tested in cross-validation and A vs. B scenarios. We present results that reveal the contributions of part-of-speech (syntactic) and semantic patterns, and suggest that the former are more consequential to the security of passwords. Our results show that in many cases PCFGs are still competitive models compared to their latest neural network counterparts. In addition, we show that there is little performance gain in training PCFGs with more than 1 million passwords. We present qualitative analyses of four password leaks (Mate1, 000webhost, Comcast, and RockYou) based on trained semantic grammars, and derive graphical models that capture high-level dependencies between token classes. Finally, we confirm the similarity inferences from our qualitative analysis by examining the effectiveness of grammars trained and tested on all pairs of leaks.
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 | 0.005 | 0.026 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".