List your company

Trigger Inversion on SST-2

1Success RateCSO(discrete)
-0.040.230.50.77Jun 30, 2026

Evaluation results

MethodLinks
CSO(discrete)Target Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.061—
CSO(discrete)Target Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.061—
CSO(discrete)Target Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060.8667—
CSO(discrete)Target Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060.8333—
CSO(discrete)Target Trigger=mb, Trigger length=1 token, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.060.3333—
CSO(discrete)Target Trigger=mb, Trigger length=1 token, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.060.3333—
CSO(discrete)Target Trigger=mb, Trigger length=1 token, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060.3—
CSO(discrete)Target Trigger=mb, Trigger length=1 token, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060.2667—
UATTarget Trigger=mb, Trigger length=1 token, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.060.2667—
UATTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060.2333—
UATTarget Trigger=mb, Trigger length=1 token, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060.1667—
UATTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060.1333—
UATTarget Trigger=mb, Trigger length=1 token, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060.1333—
PICCOLOTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060.1333—
UATTarget Trigger=mb, Trigger length=1 token, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.060.1—
DBSTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060.0667—
PICCOLOTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.060.0667—
MMTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060.0333—
MMTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.060.0333—
MMTarget Trigger=mb, Trigger length=1 token, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.060.0333—
UATTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.060.0333—
GBDATarget Trigger=mb, Trigger length=1 token, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.060.0333—
GBDATarget Trigger=mb, Trigger length=1 token, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.060.0333—
MMTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
MMTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
MMTarget Trigger=mb, Trigger length=1 token, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
MMTarget Trigger=mb, Trigger length=1 token, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060—
MMTarget Trigger=mb, Trigger length=1 token, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
DBSTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060—
DBSTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
DBSTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.060—
DBSTarget Trigger=mb, Trigger length=1 token, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
DBSTarget Trigger=mb, Trigger length=1 token, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060—
DBSTarget Trigger=mb, Trigger length=1 token, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
DBSTarget Trigger=mb, Trigger length=1 token, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.060—
UATTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
PICCOLOTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
PICCOLOTarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
GBDATarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
GBDATarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060—
GBDATarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
GBDATarget Trigger=Tell me seriously, Trigger length=3 tokens, Poisoning Type=dirty label, Poison Rate=high, Model=Qwen3-0.6b2026.060—
GBDATarget Trigger=mb, Trigger length=1 token, Poisoning Type=clean label, Poison Rate=low, Model=Qwen3-0.6b2026.060—
GBDATarget Trigger=mb, Trigger length=1 token, Poisoning Type=clean label, Poison Rate=high, Model=Qwen3-0.6b2026.060—
CSO(discrete)Model=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=low2026.06—22
CSO(discrete)Model=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=high2026.06—28
CSO(discrete)Model=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=low2026.06—30
CSO(discrete)Model=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=high2026.06—30
CSO(discrete)Model=Flan-t5-large, Trigger phrase=mb(1 token), Label type=clean label, Poison rate=low2026.06—10
CSO(discrete)Model=Flan-t5-large, Trigger phrase=mb(1 token), Label type=clean label, Poison rate=high2026.06—10
CSO(discrete)Model=Flan-t5-large, Trigger phrase=mb(1 token), Label type=dirty label, Poison rate=low2026.06—10
CSO(discrete)Model=Flan-t5-large, Trigger phrase=mb(1 token), Label type=dirty label, Poison rate=high2026.06—10
DBSModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=low2026.06—0
DBSModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=high2026.06—1
DBSModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=low2026.06—0
DBSModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=high2026.06—0
DBSModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=clean label, Poison rate=low2026.06—0
DBSModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=clean label, Poison rate=high2026.06—0
DBSModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=dirty label, Poison rate=low2026.06—0
DBSModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=dirty label, Poison rate=high2026.06—0
GBDAModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=low2026.06—0
GBDAModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=high2026.06—0
GBDAModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=low2026.06—0
GBDAModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=high2026.06—0
GBDAModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=clean label, Poison rate=low2026.06—0
GBDAModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=clean label, Poison rate=high2026.06—0
GBDAModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=dirty label, Poison rate=low2026.06—0
GBDAModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=dirty label, Poison rate=high2026.06—0
MMModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=low2026.06—2
MMModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=high2026.06—11
MMModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=low2026.06—5
MMModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=high2026.06—0
MMModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=clean label, Poison rate=low2026.06—9
MMModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=clean label, Poison rate=high2026.06—10
MMModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=dirty label, Poison rate=low2026.06—10
MMModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=dirty label, Poison rate=high2026.06—10
PICCOLOModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=low2026.06—0
PICCOLOModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=high2026.06—2
PICCOLOModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=low2026.06—6
PICCOLOModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=high2026.06—0
UATModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=low2026.06—5
UATModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=clean label, Poison rate=high2026.06—14
UATModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=low2026.06—4
UATModel=Flan-t5-large, Trigger phrase=Tell me seriously(3 tokens), Label type=dirty label, Poison rate=high2026.06—8
UATModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=clean label, Poison rate=low2026.06—1
UATModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=clean label, Poison rate=high2026.06—2
UATModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=dirty label, Poison rate=low2026.06—4
UATModel=Flan-t5-large, Trigger phrase=mb(1 token), Label type=dirty label, Poison rate=high2026.06—3