List your company

Trigger Inversion on SST2

100RecallCSO(discrete)
-4235077Jun 30, 2026

Evaluation results

MethodLinks
CSO(discrete)Model=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=low2026.06100—
CSO(discrete)Model=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=high2026.06100—
CSO(discrete)Model=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=high2026.0690—
CSO(discrete)Model=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=low2026.0683.3333—
UATModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=high2026.0636.6667—
CSO(discrete)Model=Flan-t5-small, Trigger=mb (1 token), Label Type=clean label, Poison Rate=low2026.0633.3333—
CSO(discrete)Model=Flan-t5-small, Trigger=mb (1 token), Label Type=clean label, Poison Rate=high2026.0633.3333—
CSO(discrete)Model=Flan-t5-small, Trigger=mb (1 token), Label Type=dirty label, Poison Rate=high2026.0633.3333—
UATModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=low2026.0633.3333—
CSO(discrete)Model=Flan-t5-small, Trigger=mb (1 token), Label Type=dirty label, Poison Rate=low2026.0630—
UATModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=high2026.0626.6667—
UATModel=Flan-t5-small, Trigger=mb (1 token), Label Type=dirty label, Poison Rate=high2026.0626.6667—
UATModel=Flan-t5-small, Trigger=mb (1 token), Label Type=clean label, Poison Rate=high2026.0616.6667—
UATModel=Flan-t5-small, Trigger=mb (1 token), Label Type=dirty label, Poison Rate=low2026.0616.6667—
PICCOLOModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=high2026.0616.6667—
UATModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=low2026.0613.3333—
DBSModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=low2026.0610—
DBSModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=high2026.0610—
PICCOLOModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=low2026.0610—
DBSModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=high2026.066.6667—
DBSModel=Flan-t5-small, Trigger=mb (1 token), Label Type=clean label, Poison Rate=high2026.066.6667—
PICCOLOModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=high2026.066.6667—
GBDAModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=low2026.066.6667—
MMModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=high2026.063.3333—
MMModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=high2026.063.3333—
MMModel=Flan-t5-small, Trigger=mb (1 token), Label Type=dirty label, Poison Rate=high2026.063.3333—
DBSModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=low2026.063.3333—
UATModel=Flan-t5-small, Trigger=mb (1 token), Label Type=clean label, Poison Rate=low2026.063.3333—
MMModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=low2026.060—
MMModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=low2026.060—
MMModel=Flan-t5-small, Trigger=mb (1 token), Label Type=clean label, Poison Rate=low2026.060—
MMModel=Flan-t5-small, Trigger=mb (1 token), Label Type=clean label, Poison Rate=high2026.060—
MMModel=Flan-t5-small, Trigger=mb (1 token), Label Type=dirty label, Poison Rate=low2026.060—
DBSModel=Flan-t5-small, Trigger=mb (1 token), Label Type=clean label, Poison Rate=low2026.060—
DBSModel=Flan-t5-small, Trigger=mb (1 token), Label Type=dirty label, Poison Rate=low2026.060—
DBSModel=Flan-t5-small, Trigger=mb (1 token), Label Type=dirty label, Poison Rate=high2026.060—
PICCOLOModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=low2026.060—
GBDAModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=clean label, Poison Rate=high2026.060—
GBDAModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=low2026.060—
GBDAModel=Flan-t5-small, Trigger=Tell me seriously (3 tokens), Label Type=dirty label, Poison Rate=high2026.060—
GBDAModel=Flan-t5-small, Trigger=mb (1 token), Label Type=clean label, Poison Rate=low2026.060—
GBDAModel=Flan-t5-small, Trigger=mb (1 token), Label Type=clean label, Poison Rate=high2026.060—
GBDAModel=Flan-t5-small, Trigger=mb (1 token), Label Type=dirty label, Poison Rate=low2026.060—
GBDAModel=Flan-t5-small, Trigger=mb (1 token), Label Type=dirty label, Poison Rate=high2026.060—
ALTModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=clean label2026.06—12
ALTModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=dirty label2026.06—10
ALTModel=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=clean label2026.06—10
ALTModel=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=dirty label2026.06—10
CSO(discrete)Model=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=clean label2026.06—25
CSO(discrete)Model=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=dirty label2026.06—30
CSO(discrete)Model=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=clean label2026.06—10
CSO(discrete)Model=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=dirty label2026.06—10
DBSModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=clean label2026.06—0
DBSModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=dirty label2026.06—2
DBSModel=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=clean label2026.06—3
DBSModel=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=dirty label2026.06—2
GBDAModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=clean label2026.06—0
GBDAModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=dirty label2026.06—3
GBDAModel=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=clean label2026.06—0
GBDAModel=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=dirty label2026.06—0
MMModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=clean label2026.06—5
MMModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=dirty label2026.06—8
MMModel=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=clean label2026.06—10
MMModel=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=dirty label2026.06—10
PICCOLOModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=clean label2026.06—2
PICCOLOModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=dirty label2026.06—3
UATModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=clean label2026.06—1
UATModel=Qwen3-4b, Poison Rate=high, Target Trigger=Tell me seriously(3 tokens), Labeling Strategy=dirty label2026.06—2
UATModel=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=clean label2026.06—5
UATModel=Qwen3-4b, Poison Rate=high, Target Trigger=mb(1 token), Labeling Strategy=dirty label2026.06—8