PhishSigma++ reaches 0.9675 F1 on clean data and holds 0.9579 F1 under adversarial text padding by modeling typed entity relations in emails, outperforming text-only baselines that drop sharply.
Holmes: real-time apt detection through correlation of sus- picious information flows
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
-
PhishSigma++: Malicious Email Detection with Typed Entity Relations
PhishSigma++ reaches 0.9675 F1 on clean data and holds 0.9579 F1 under adversarial text padding by modeling typed entity relations in emails, outperforming text-only baselines that drop sharply.