The Tables Have Turned: GPT-3 Distinguishing Passwords from Honeywords
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
In the field of information security, there has been a noteworthy trend toward leveraging machine learning models to develop and exploit security solutions. The emergence of Generative Pre-trained Transformer: version 3 (GPT-3), a pre-trained language model developed by OpenAI, has generated considerable excitement due to its unprecedented ability to generate different solutions. In the realm of timely detecting threats on a password-file, the generation of realistic yet fictitious passwords or honeywords has long been recognized as a crucial aspect of security solutions. However, meeting this requirement has proven to be a persistent challenge. In the face of this crisis, researchers have recently proposed employing GPT-3 as a means to surpass this barrier. This paper presents an analysis of how GPT-3 can potentially undermine the effectiveness of this security solution by accurately distinguishing genuine passwords from a set of honeywords it generates. The experiments conducted for this study reveal that GPT-3 can accurately guess a significant percentage of actual passwords, reaching as high as 53.45% with just three attempts. Though we emphasize the careful use of GPT-3 for generating honeywords, one of the primary findings in this study strongly indicates that GPT-3 can effectively be transformed into an attack mechanism, thus altering the dynamics of the present notion.
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 | 0.001 | 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 | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
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