Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Prompt Injection Robustness on TensorTrust hijacking and extraction (full dataset)
Loading...
98.1
HRR
No-ISE
15.42
36.885
58.35
79.815
Jun 9, 2026
HRR
ERR
Macro Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
HRR
ERR
Macro Score
No-ISE
configuration=Indiscri...
2026.06
98.1
95.8
96.9
DPO
configuration=Standard...
2026.06
91.8
89.5
90.6
GW-DPO (lin.)
configuration=Gravity-...
2026.06
89.6
81.8
85.7
3-level (lin.)
configuration=3-level...
2026.06
87.1
90.9
89
GW-DPO (bi.)
configuration=Gravity-...
2026.06
85.4
78.1
81.8
Llama-3.1-Instruct
configuration=off-the-...
2026.06
25.8
16.7
21.2
SFT
configuration=Supervis...
2026.06
22.2
56.1
39.2
baseline
configuration=baseline
2026.06
18.6
16.8
17.7
Feedback
Search any
task
Search any
task