X-MAP: eXplainable Misclassification Analysis and Profiling for Spam and Phishing Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912909505855488 |
|---|---|
| author | Zhang, Qi Chen, Dian Kaplan, Lance M. Jøsang, Audun Jeong, Dong Hyun Chen, Feng Cho, Jin-Hee |
| author_facet | Zhang, Qi Chen, Dian Kaplan, Lance M. Jøsang, Audun Jeong, Dong Hyun Chen, Feng Cho, Jin-Hee |
| contents | Misclassifications in spam and phishing detection are very harmful, as false negatives expose users to attacks while false positives degrade trust. Existing uncertainty-based detectors can flag potential errors, but possibly be deceived and offer limited interpretability. This paper presents X-MAP, an eXplainable Misclassification Analysis and Profilling framework that reveals topic-level semantic patterns behind model failures. X-MAP combines SHAP-based feature attributions with non-negative matrix factorization to build interpretable topic profiles for reliably classified spam/phishing and legitimate messages, and measures each message's deviation from these profiles using Jensen-Shannon divergence. Experiments on SMS and phishing datasets show that misclassified messages exhibit at least two times larger divergence than correctly classified ones. As a detector, X-MAP achieves up to 0.98 AUROC and lowers the false-rejection rate at 95% TRR to 0.089 on positive predictions. When used as a repair layer on base detectors, it recovers up to 97% of falsely rejected correct predictions with moderate leakage. These results demonstrate X-MAP's effectiveness and interpretability for improving spam and phishing detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15298 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | X-MAP: eXplainable Misclassification Analysis and Profiling for Spam and Phishing Detection Zhang, Qi Chen, Dian Kaplan, Lance M. Jøsang, Audun Jeong, Dong Hyun Chen, Feng Cho, Jin-Hee Artificial Intelligence Misclassifications in spam and phishing detection are very harmful, as false negatives expose users to attacks while false positives degrade trust. Existing uncertainty-based detectors can flag potential errors, but possibly be deceived and offer limited interpretability. This paper presents X-MAP, an eXplainable Misclassification Analysis and Profilling framework that reveals topic-level semantic patterns behind model failures. X-MAP combines SHAP-based feature attributions with non-negative matrix factorization to build interpretable topic profiles for reliably classified spam/phishing and legitimate messages, and measures each message's deviation from these profiles using Jensen-Shannon divergence. Experiments on SMS and phishing datasets show that misclassified messages exhibit at least two times larger divergence than correctly classified ones. As a detector, X-MAP achieves up to 0.98 AUROC and lowers the false-rejection rate at 95% TRR to 0.089 on positive predictions. When used as a repair layer on base detectors, it recovers up to 97% of falsely rejected correct predictions with moderate leakage. These results demonstrate X-MAP's effectiveness and interpretability for improving spam and phishing detection. |
| title | X-MAP: eXplainable Misclassification Analysis and Profiling for Spam and Phishing Detection |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.15298 |