Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Malicious Behavior Defense in Multi-Agent Systems on S-PI (GSM8K)
Loading...
3
ASR
AcMAS
-0.44
22.78
46
69.22
Jul 7, 2026
ASR
TCR
Updated 16d ago
Evaluation Results
Method
Method
Links
ASR
TCR
AcMAS
2026.07
3
100
G-Safeguard
2026.07
17
90
BlindGuard
2026.07
23
84
No Defense
2026.07
89
-
Feedback
Search any
task
Search any
task