"Dalhousie NIMS Lab IMA Traffic Dataset 2025"
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
"This dataset presents encrypted network traffic flows captured from eight Instant Messaging Applications (IMAs), simulating group chat scenarios across multiple devices in a controlled cloud environment. Our methodology utilized a set of automated orchestration scripts to simulate realistic user behavior\u2014such as asynchronous conversations and app switching\u2014using Android Cuttlefish emulators. This approach allowed us to minimize background noise and isolate meaningful IMA communication traffic. The dataset consists of flow-level metadata collected from the following eight IMAs: Discord, Messenger, Rocket.Chat, Slack, Skype, Signal, Teams, and Telegram These flows were extracted from .pcap captures using Tranalyzer2, and include feature-rich session-level metadata useful for application identification, device fingerprinting, and user action classification (e.g., distinguishing group chat activity across applications). Each application\u2019s traffic is stored in a structured format and labeled with device and action metadata. The dataset supports both encrypted and TLS-SNI-disambiguated flows, allowing for flexible downstream analysis. Comprehensive details regarding our traffic generation, emulation architecture, and labeling methodology are provided in our accompanying paper. A structured README further explains the folder hierarchy, features, and filtering logic. This dataset serves as a valuable resource for researchers exploring encrypted traffic analysis, identity-aware network monitoring, and ML-based Zero Trust policy enforcement."
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.007 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.005 | 0.044 |
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