AUTHOR
No models indexed under this account. Publishes 6 alignment datasets (6.2k downloads) tracked in our /datasets catalog.
Alignment datasets by
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.
Dataset
Stage
Downloads
Likes
agentic-prompt-injection-boundary-pairs 0 0
Agentic Prompt-Injection Boundary Pairs
Most prompt-injection datasets make the attack easy to recognize. The malicious row contains obv...
2k
6
turkish-conversation-prompt-injection 0 0
Turkish Conversation Prompt-Injection Dataset
Canonical dataset release:
Hugging Face
hosts the dataset viewer and downloads. This ...
1.7k
4
agentic-prompt-injection-5k 0 0
Agentic Prompt-Injection 5K
5,000 examples of agentic and indirect prompt injection. A curated, paired benign/attack dataset for evaluati...
1.1k
3
guardrail-hard-negatives 0 0
Guardrail Hard Negatives (EN/TR)
A false-positive stress test for guardrails. A curated, paired benign/attack dataset for evaluating and ...
468
5
turkish-prompt-injection-1k 0 0
Turkish Prompt-Injection 1K
1,000 Turkish-native examples. A curated, paired benign/attack dataset for evaluating and training prompt-inj...
441
2
english-prompt-injection-3k 0 0
English Prompt-Injection 3K
3,000 examples of direct prompt injection across eight families. A curated, paired benign/attack dataset for ...
437
2
Dataset
Stage
Downloads
Likes
guardrail-hard-negatives 0 0
Guardrail Hard Negatives (EN/TR)
A false-positive stress test for guardrails. A curated, paired benign/attack dataset for evaluating and ...
468
5
turkish-prompt-injection-1k 0 0
Turkish Prompt-Injection 1K
1,000 Turkish-native examples. A curated, paired benign/attack dataset for evaluating and training prompt-inj...
441
2
agentic-prompt-injection-5k 0 0
Agentic Prompt-Injection 5K
5,000 examples of agentic and indirect prompt injection. A curated, paired benign/attack dataset for evaluati...
1.1k
3
english-prompt-injection-3k 0 0
English Prompt-Injection 3K
3,000 examples of direct prompt injection across eight families. A curated, paired benign/attack dataset for ...
437
2
agentic-prompt-injection-boundary-pairs 0 0
Agentic Prompt-Injection Boundary Pairs
Most prompt-injection datasets make the attack easy to recognize. The malicious row contains obv...
2k
6
turkish-conversation-prompt-injection 0 0
Turkish Conversation Prompt-Injection Dataset
Canonical dataset release:
Hugging Face
hosts the dataset viewer and downloads. This ...
1.7k
4
Dataset
Stage
Downloads
Likes
agentic-prompt-injection-boundary-pairs 0 0
Agentic Prompt-Injection Boundary Pairs
Most prompt-injection datasets make the attack easy to recognize. The malicious row contains obv...
2k
6
guardrail-hard-negatives 0 0
Guardrail Hard Negatives (EN/TR)
A false-positive stress test for guardrails. A curated, paired benign/attack dataset for evaluating and ...
468
5
turkish-conversation-prompt-injection 0 0
Turkish Conversation Prompt-Injection Dataset
Canonical dataset release:
Hugging Face
hosts the dataset viewer and downloads. This ...
1.7k
4
agentic-prompt-injection-5k 0 0
Agentic Prompt-Injection 5K
5,000 examples of agentic and indirect prompt injection. A curated, paired benign/attack dataset for evaluati...
1.1k
3
turkish-prompt-injection-1k 0 0
Turkish Prompt-Injection 1K
1,000 Turkish-native examples. A curated, paired benign/attack dataset for evaluating and training prompt-inj...
441
2
english-prompt-injection-3k 0 0
English Prompt-Injection 3K
3,000 examples of direct prompt injection across eight families. A curated, paired benign/attack dataset for ...
437
2