SISA training lets RL ransomware detectors forget selected samples by retraining one shard, with under 0.05% F1 drop and much lower retraining cost than full retraining.
Singh, Saket Sarin, Chandra Kumari Subba, Varsha Arya, N
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Privacy-Aware Machine Unlearning with SISA for Reinforcement Learning-Based Ransomware Detection
SISA training lets RL ransomware detectors forget selected samples by retraining one shard, with under 0.05% F1 drop and much lower retraining cost than full retraining.