Get the app
← back to catalog
AUTHOR

Cyber-security-final-project

No models indexed under this account. Publishes 3 alignment datasets (3.2k downloads) tracked in our /datasets catalog.

Alignment datasets by Cyber-security-final-project

Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.

3 in /datasets
Dataset
Stage
Downloads
Generated_Injected_PDFs_HARMLESS 0 0
Generated Injected PDFs — HARMLESS A synthetic dataset of 1,100 PDF files built for training and evaluating structural PDF-malware detect...
misc
2.1k
HARMLESS_Synthetic_Injected_PDFs_EDA 0 0
Injected PDFs - EDA and Evaluation Corpus This repository holds the exploratory data analysis for a project on detecting harmless-but-rea...
misc
617
Evaluation_of_OpenSource_Models_for_PDF_Injection_Recognition 0 0
Injected PDFs - Model Evaluation This repository holds the model evaluation stage of a project on detecting harmless-but-real attack payl...
evaluate
402
Dataset
Stage
Downloads
Evaluation_of_OpenSource_Models_for_PDF_Injection_Recognition 0 0
Injected PDFs - Model Evaluation This repository holds the model evaluation stage of a project on detecting harmless-but-real attack payl...
evaluate
402
HARMLESS_Synthetic_Injected_PDFs_EDA 0 0
Injected PDFs - EDA and Evaluation Corpus This repository holds the exploratory data analysis for a project on detecting harmless-but-rea...
misc
617
Generated_Injected_PDFs_HARMLESS 0 0
Generated Injected PDFs — HARMLESS A synthetic dataset of 1,100 PDF files built for training and evaluating structural PDF-malware detect...
misc
2.1k
Dataset
Stage
Downloads
Generated_Injected_PDFs_HARMLESS 0 0
Generated Injected PDFs — HARMLESS A synthetic dataset of 1,100 PDF files built for training and evaluating structural PDF-malware detect...
misc
2.1k
HARMLESS_Synthetic_Injected_PDFs_EDA 0 0
Injected PDFs - EDA and Evaluation Corpus This repository holds the exploratory data analysis for a project on detecting harmless-but-rea...
misc
617
Evaluation_of_OpenSource_Models_for_PDF_Injection_Recognition 0 0
Injected PDFs - Model Evaluation This repository holds the model evaluation stage of a project on detecting harmless-but-real attack payl...
evaluate
402
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration