Dataset Viewer
Auto-converted to Parquet Duplicate
messages
listlengths
3
3
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
[ { "role": "system", "content": "You are an on-device scam detector for Indian users. Assess the latest message window and reply with strict JSON: {\"scam_probability\": <0.0-1.0>, \"tactics\": [<matching tactic ids>], \"warning\": \"<if risky, one short warning in the user's language; else empty string>\"}"...
End of preview. Expand in Data Studio

BSIS: Indian Scam Message Detection Dataset

Synthetic training data for on-device scam detection on Indian SMS and WhatsApp traffic. Every row was produced by the BSIS red-team/blue-team simulation arena: a scammer (or a genuine sender) talks to a simulated victim in an Indian language, and a privacy-preserving defender scores each message. Labels come from deterministic Rust logic over ground truth, never from model opinion. This dataset is synthetic. It contains no real user messages, and no real personal data.

Splits

config train validation test
classifier 32858 2148 1883
chatml 28957 1905 1607

Splits are grouped by lineage. All mutated generations of one scenario stay in the same split, so no adversarial sibling leaks across train, validation or test.

Label balance (classifier)

label rows
0 (safe until this round) 14598
1 (scam detectable at this round) 22291

Label 1 marks the sender turns from which a careful human could tell the message is a scam (judge earliest_detectable_round). Earlier turns of the same scam carry label 0 and teach the detector not to false-alarm during grooming.

Languages

All 23 Sarvam-supported Indian languages: 22 Scheduled languages plus Indian English. Odia uses the od-IN code.

language train validation test
as-IN 1017 88 89
bn-IN 2322 144 153
brx-IN 893 83 61
doi-IN 882 72 58
en-IN 1866 135 118
gu-IN 1309 83 73
hi-IN 4654 257 224
kn-IN 1371 64 68
kok-IN 905 69 60
ks-IN 857 62 51
mai-IN 890 76 56
ml-IN 1233 48 72
mni-IN 796 73 50
mr-IN 2208 109 101
ne-IN 877 70 51
od-IN 1139 78 25
pa-IN 1315 87 67
sa-IN 859 75 45
sat-IN 917 77 59
sd-IN 1057 83 63
ta-IN 2117 127 128
te-IN 2103 136 142
ur-IN 1271 52 69

Vectors

Nine scam playbooks grounded in RBI BE(A)WARE and I4C advisories, plus four hard negatives (genuine senders). Hard negatives make up roughly a quarter of lineages, so the detector learns not to flag ordinary bank alerts, doorstep delivery OTP requests, bill reminders and family messages.

vector train validation test
digital_arrest 3077 117 270
fake_courier_customs 2836 127 114
fake_customer_care 3227 233 232
kyc_utility_panic 2568 96 166
legit_bank_alert 1646 108 66
legit_delivery_otp 1485 71 63
legit_electricity_reminder 2025 98 73
legit_family_transfer 1700 108 107
predatory_loan_app 2472 349 94
qr_code_refund_trap 3346 237 145
social_friend_emergency 2813 237 105
upi_collect_trap 2771 136 197
whatsapp_stock_task 2892 231 251

Schema

classifier

  • text (string): the message window, all sender turns up to and including the current one, prefixed SENDER: / RECIPIENT:.
  • label (int64): 1 if the scam is detectable at this round, else 0.
  • language (string): BCP-47 code, for example hi-IN or od-IN.
  • script_mode (string): native_script or romanized_codemix.
  • vector (string): the scam playbook or legitimate scenario name.
  • round (int64): the sender turn number.
  • lineage_id (string): UUIDv5 of the scenario lineage. Rows sharing a lineage belong to the same conversation family.
  • hard_example (bool): the defender missed, was late, or false-alarmed.

chatml

  • messages (list of {role, content}): a three-message conversation: a short detector system prompt, the user window, and a strict-JSON assistant reply with scam_probability, tactics and warning.

Positive windows without an agreeing on-device warning are excluded from chatml and kept in classifier only, so the assistant target never invents a warning.

Provenance and safety

  • Synthetic only. Generated on the Sarvam Token Factory platform with red-team prompts restricted to placeholders: +91-98XXX-XXXXX, http://example-<word>.invalid, name@fakeupi, XXXX XXXX 1234.
  • Every generated message passed a regex PII scrubber before storage, and this package re-checks each exported row for raw Indian mobile numbers, Aadhaar patterns, PAN patterns and non-.invalid URLs. The check passes with zero hits.
  • A deterministic script check rejected conversations written in the wrong script before verification: Romanized rows stay ASCII, native rows match the expected Unicode block per language.
  • A held-out set of real, anonymized messages is kept separately and is not part of this package.

Use

from datasets import load_dataset

dataset = load_dataset("harshcasper/bsis", "classifier")

License

This dataset is released for research and educational use in scam detection and cyber-safety training. It is synthetic and carries no warranty. Do not use it to contact anyone or to send any message. If you need a different license, open an issue in the source repository.

Downloads last month
38

Models trained or fine-tuned on harshcasper/bsis