tokenizer-security-suite / LAYERFAULT_CORPUS.json
izm1chael's picture
Publish Layerfault synthetic corpus LF-CORPUS-TOK-0001
0f710e7 verified
Raw
History Blame Contribute Delete
743 Bytes
{
"candidate_rules": [
"LF-TOKENIZER-EOS-BOS-CONFLICT",
"LF-TOKENIZER-HIDDEN-PROMPT",
"LF-TOKENIZER-ROLE-BOUNDARY-CONTROL",
"LF-TOKENIZER-ROLE-REMAP",
"LF-TOKENIZER-SECURITY-DELTA",
"LF-TOKENIZER-TOOL-TEMPLATE-RISK"
],
"corpus_id": "LF-CORPUS-TOK-0001",
"description": "Clean and manipulated tokenizer variants for EOS/BOS, hidden prompt, role remap, role-boundary and tool-template comparisons.",
"expected_rules": [],
"generator": "tokenizers.tokenizer_suite",
"ground_truth": "synthetic-generated",
"must_not_rules": [],
"repo_name": "tokenizer-security-suite",
"repo_type": "model",
"safety": "inert/canary-only",
"schema": 1,
"validation": {
"kind": "manual",
"target": "."
}
}