Alignment datasets by AltaySec

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.

2 in /datasets
Dataset
Stage
Downloads
turkish-llm-injection 0 0
🇹🇷 AltaySec Turkish LLM Prompt Injection Dataset (v0.2) Türkiye'nin ilk Türkçe-öncelikli, kategorize edilmiş LLM prompt injection veri ...
912
altayduel-transcripts 0 0
🥊 AltayDuel — Agent-vs-Agent Prompt Injection Transcripts (v0.2) Çok-turlu Türkçe + İngilizce prompt-injection düello transkriptleri. Al...
401
Dataset
Stage
Downloads
altayduel-transcripts 0 0
🥊 AltayDuel — Agent-vs-Agent Prompt Injection Transcripts (v0.2) Çok-turlu Türkçe + İngilizce prompt-injection düello transkriptleri. Al...
401
turkish-llm-injection 0 0
🇹🇷 AltaySec Turkish LLM Prompt Injection Dataset (v0.2) Türkiye'nin ilk Türkçe-öncelikli, kategorize edilmiş LLM prompt injection veri ...
912
Dataset
Stage
Downloads
turkish-llm-injection 0 0
🇹🇷 AltaySec Turkish LLM Prompt Injection Dataset (v0.2) Türkiye'nin ilk Türkçe-öncelikli, kategorize edilmiş LLM prompt injection veri ...
912
altayduel-transcripts 0 0
🥊 AltayDuel — Agent-vs-Agent Prompt Injection Transcripts (v0.2) Çok-turlu Türkçe + İngilizce prompt-injection düello transkriptleri. Al...
401
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.

Open in Abliteration