# CyberCane: Neuro-Symbolic RAG for Privacy-Preserving Phishing Detection with Formal Ontology Reasoning

arXiv: https://arxiv.org/abs/2604.23563 · HTML: https://mlsanity.com/paper/2604.23563/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Builds on (most cited first, 11 of 11)

- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [Harnessing Deep Neural Networks with Logic Rules](https://mlsanity.com/paper/1603.06318/) (2016)
- [Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence](https://mlsanity.com/paper/2305.03010/) (2023)
- [KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection](https://mlsanity.com/paper/2403.02253/) (2024)
- [ChatSpamDetector: Leveraging Large Language Models for Effective Phishing Email Detection](https://mlsanity.com/paper/2402.18093/) (2024)
- [SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation](https://mlsanity.com/paper/2506.12699/) (2025)
- [MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation](https://mlsanity.com/paper/2407.15748/) (2024)
- [SymRAG: Efficient Neuro-Symbolic Retrieval Through Adaptive Query Routing](https://mlsanity.com/paper/2506.12981/) (2025)
- [Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities](https://mlsanity.com/paper/2509.06921/) (2025)

## Abstract (arXiv)

Privacy-critical domains require phishing detection systems that satisfy contradictory constraints: near-zero false positives to prevent workflow disruption, transparent explanations for non-expert staff, strict regulatory compliance prohibiting sensitive data exposure to external APIs, and robustness against AI-generated attacks. Existing rule-based systems are brittle to novel campaigns, while LLM-based detectors violate privacy regulations through unredacted data transmission. We introduce CyberCane, a neuro-symbolic framework integrating deterministic symbolic analysis with privacy-preserving retrieval-augmented generation (RAG). Our dual-phase pipeline applies lightweight symbolic rules to email metadata, then escalates borderline cases to semantic classification via RAG with automated sensitive data redaction and retrieval from a phishing-only corpus. We further introduce PhishOnt, an OWL ontology enabling verifiable attack classification through formal reasoning chains. Evaluation on DataPhish2025 (12.3k emails; mixed human/LLM) and Nazario/SpamAssassin demonstrates a 78.6-point recall gain over symbolic-only detection on AI-generated threats, with precision exceeding 98% and FPR as low as 0.16%. Healthcare deployment projects a 542x ROI; tunable operating points support diverse risk tolerances, with open-source implementation at https://github.com/sbhakim/Cybercane.