← Back to all news
arXiv Machine Learning By Warren Fernando, Nikos Komninos

Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems

Read the original on arXiv Machine Learning →

arXiv:2606. 11471v1 Announce Type: cross Abstract: The expansion of the digital domain has resulted in a substantial increase in digital communication, with email emerging as one of the most prominent channels.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 18

AURA: Adaptive Uncertainty-Routed Analysis for Email Threat Detection

AURA: Adaptive Uncertainty-Routed Analysis for Email Threat Detection is a multimodal system that evaluates both email content and embedded URLs to detect spam and phishing. It uses a two-layer approach: first, a URL classifier estimates prediction uncertainty, and only messages with high uncertainty are passed to a fine-tuned transformer encoder for deeper semantic analysis. Evaluated on eight diverse training corpora and two real-world datasets covering a decade of attacks, AURA achieves a macro F1-score of 0.9858 in-distribution and maintains scores above 0.94 on the NazPhish-Eval and GuenterTrap-Eval datasets, demonstrating strong generalization to new attack scenarios.

By Omran Berjawi, Walid fahs, Rida Khatoun
llmsfine-tuningmultimodalsafety
More like this →
arXiv Computation and Language
6d ago

Prompt Injection Detection for Email Agents Through Attack Chain Modeling

The paper introduces a prompt‑injection detection framework for email assistants that models attacks as a chain of stages. It combines a text detector, stage‑specific verifiers, rule‑based risk signals, user intent consistency checks, and a logistic decision policy. Experiments on five benchmarks show the framework outperforms pretrained detectors, achieving a mean F1 of 0.406 versus 0.216, and demonstrate that training on benign emails resembling attacks reduces false alarms.

By Ahmad Hashmi, Dhyey Patel, Yunting Yin
llmsagentsnlpbenchmarks
More like this →