A fine-tuning framework reduces PGD attack success on AdvDA detectors from 100% to 3.2% and MalGuise from 13% to 5.1%, but optimal training strategies differ by threat model and robustness does not transfer across them.
In: 2022 IEEE Symposium on Security and Privacy (SP)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
MalwarePT is a ModernBERT-style binary foundation model pretrained with masked language modeling on PE code bytes using BPE tokenization that transfers to API call prediction, functionality classification, and temporal-drift malware detection.
citing papers explorer
-
Can Drift-Adaptive Malware Detectors Be Made Robust? Attacks and Defenses Under White-Box and Black-Box Threats
A fine-tuning framework reduces PGD attack success on AdvDA detectors from 100% to 3.2% and MalGuise from 13% to 5.1%, but optimal training strategies differ by threat model and robustness does not transfer across them.
-
MalwarePT: A Binary-Level Foundation Model for Malware Analysis
MalwarePT is a ModernBERT-style binary foundation model pretrained with masked language modeling on PE code bytes using BPE tokenization that transfers to API call prediction, functionality classification, and temporal-drift malware detection.