RETROFIT enables continual learning for malware detection and binary summarization by retrospective-free parameter merging with low-rank sparse updates and confidence-guided arbitration, improving retention and generalization without historical data.
Revisit- ing non-separable binary classification and its applications in anomaly detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis
RETROFIT enables continual learning for malware detection and binary summarization by retrospective-free parameter merging with low-rank sparse updates and confidence-guided arbitration, improving retention and generalization without historical data.