PiMRef is proposed, the first reference-based solution to detect ever-evolving phishing emails using knowledge-based invariants, targeting the identity-impersonation attacks that characterize spear-phishing.
Abstract
Phishing email is a critical step in the cybercrime kill chain due to the high reachability of victims'email accounts and the low cost of launching phishing campaigns. This ever-evolving nature of phishing emails makes traditional rule-based and feature-engineering-based phishing email detectors fight an uphill battle in the cat-and-mouse game of defense and attack. In this work, we show that, large language models (LLMs) can be effectively exploited to generate profile-grounded spear-phishing, compromising major paradigms of phishing email detectors. To defend against such LLM-based spear-phishing attacks, we propose PiMRef, the first reference-based solution to detect ever-evolving phishing emails using knowledge-based invariants, targeting the identity-impersonation attacks that characterize spear-phishing. Our rationale lies in the fact that convincing phishing emails often include ``disprovable claims'', which contradict certain real-world facts. Technically, given an email, PiMRef (i) discovers the claimed identity of the sender, (ii) verifies the sender's email domain against a dynamically expandable knowledge base, and (iii) infers call-to-action instructions that encourage next-step engagement. Compared to existing baselines such as D-Fence, HelpHed, and ChatSpamDetector, PimRef reduces the false-positive rate to 0.81\% while maintaining a recall of 90.7\%-93.1\% on conventional phishing benchmarks such as Nazario and PhishPot. On SpearMail, our newly constructed benchmark of 14,672 LLM-generated spear-phishing emails targeting 681 public profiles, PimRef reaches a recall of 86.4\% without incurring additional false positives. Our code is publicly available at https://github.com/code-philia/PhishEmail.
In recent years, phishing attacks have grown exponentially in scale, frequency, and sophistication, placing a significant burden on organizations and security personnel. Attackers leverage advanced obfuscation techniques to evade detection systems and ensure their emails reach users’ inboxes. Additionally, attackers di...
Language model agents are increasingly deployed to automate everyday digital chores from managing emails and social media to handling banking and bills allowing users to step away from supervision. However, this capability also exposes sensitive information to phishing. Safe execution requires distinguishing malicious...
Rafid Ahmed, Joseph Fioresi, Mubarak Shah et al.· 0 citations
It is found that attackers diversify what they use to deceive but converge on how victims should respond: no theme exceeds 21.3% of emails, while a single CTA, URL navigation, accounts for 73.0% and impersonation choices are conditioned on theme.
Jaehwan Park, Woonghee Lee, Fu-Jiao Ji et al.· arXiv.org· 0 citations
While general-purpose large language models (LLMs) represent a new frontier in cybersecurity, their effectiveness for specialized tasks such as phishing detection requires further empirical validation. This research systematically compares the effectiveness of three industry-leading models, which were selected by the r...
Chandregowda Pachegowda, Joseph C. Brickley, Abdullah Alhayajneh et al.· 2026 International Conferenc...· 0 citations
Phishing has evolved from simple fraudulent messages into a multi-channel credential-theft ecosystem thatcombines malicious URLs, QR-code phishing, adversary-in-the-middle proxying, business e-mail compromise,deepfake-assisted social engineering, and generative-AI-assisted content generation. This paper proposes anexpl...
M. Albareda· مجلة جامعة صنعاء للعلوم التط...· 0 citations
Large language models (LLMs) can explain phishing verdicts in natural language, but using them as the detector adds latency and cost, and their explanations can cite evidence that is absent or wrong. We present PhishLens, a phishing website detector in which frozen classical models set every phishing label and probabil...
S. Nandhini, M. Saranya, P. M. G. Jegathambal· International Journal of Eng...· 0 citations