@inproceedings{vyas-etal-2026-sentineledge,
title = "{S}entinel{E}dge: A Lightweight, Streaming, Auditable Scam-Call Detection System for the Edge",
author = "Vyas, Mayank and
Agarwal, Shiven and
Nag, Prisha and
Sharma, Ishita Rajesh and
Chakraborty, Abhijit and
Gupta, Vivek",
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.60/",
pages = "625--638",
ISBN = "979-8-89176-461-3",
abstract = "We present SENTINELEDGE, an open-source streaming detector for English-language scam phone calls that scores speech sentence-by- sentence and raises alerts while a conversa- tion is in progress, protecting callers rather than explaining losses afterward. It targets multi-minute scripted fraud calls, where sys- tems are closed and un-auditable and aca- demic alternatives use neural backbones un- suited to on-device budgets. SENTINELEDGE uses a streaming framework with per-sentence scoring, exponential moving average smooth- ing, and threshold-triggered alerts. It com- pares classifier heads using hand-crafted fea- tures, TF{--}IDF, SVM, gradient-boosted trees, and fine-tuned transformer on identical inputs and robustness conditions, revealing storage{--} accuracy trade-offs. We report bootstrap con- fidence intervals, stress-test ASR-style noise, adversarial scam phrasings and retraining, and zero-shot transfer to SMS and phishing URLs. Code, models, evaluation harness, and demon- stration are released under the MIT license"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vyas-etal-2026-sentineledge">
<titleInfo>
<title>SentinelEdge: A Lightweight, Streaming, Auditable Scam-Call Detection System for the Edge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mayank</namePart>
<namePart type="family">Vyas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiven</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prisha</namePart>
<namePart type="family">Nag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ishita</namePart>
<namePart type="given">Rajesh</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhijit</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>We present SENTINELEDGE, an open-source streaming detector for English-language scam phone calls that scores speech sentence-by- sentence and raises alerts while a conversa- tion is in progress, protecting callers rather than explaining losses afterward. It targets multi-minute scripted fraud calls, where sys- tems are closed and un-auditable and aca- demic alternatives use neural backbones un- suited to on-device budgets. SENTINELEDGE uses a streaming framework with per-sentence scoring, exponential moving average smooth- ing, and threshold-triggered alerts. It com- pares classifier heads using hand-crafted fea- tures, TF–IDF, SVM, gradient-boosted trees, and fine-tuned transformer on identical inputs and robustness conditions, revealing storage– accuracy trade-offs. We report bootstrap con- fidence intervals, stress-test ASR-style noise, adversarial scam phrasings and retraining, and zero-shot transfer to SMS and phishing URLs. Code, models, evaluation harness, and demon- stration are released under the MIT license</abstract>
<identifier type="citekey">vyas-etal-2026-sentineledge</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.60/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>625</start>
<end>638</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SentinelEdge: A Lightweight, Streaming, Auditable Scam-Call Detection System for the Edge
%A Vyas, Mayank
%A Agarwal, Shiven
%A Nag, Prisha
%A Sharma, Ishita Rajesh
%A Chakraborty, Abhijit
%A Gupta, Vivek
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F vyas-etal-2026-sentineledge
%X We present SENTINELEDGE, an open-source streaming detector for English-language scam phone calls that scores speech sentence-by- sentence and raises alerts while a conversa- tion is in progress, protecting callers rather than explaining losses afterward. It targets multi-minute scripted fraud calls, where sys- tems are closed and un-auditable and aca- demic alternatives use neural backbones un- suited to on-device budgets. SENTINELEDGE uses a streaming framework with per-sentence scoring, exponential moving average smooth- ing, and threshold-triggered alerts. It com- pares classifier heads using hand-crafted fea- tures, TF–IDF, SVM, gradient-boosted trees, and fine-tuned transformer on identical inputs and robustness conditions, revealing storage– accuracy trade-offs. We report bootstrap con- fidence intervals, stress-test ASR-style noise, adversarial scam phrasings and retraining, and zero-shot transfer to SMS and phishing URLs. Code, models, evaluation harness, and demon- stration are released under the MIT license
%U https://aclanthology.org/2026.emnlp-demos.60/
%P 625-638
Markdown (Informal)
[SentinelEdge: A Lightweight, Streaming, Auditable Scam-Call Detection System for the Edge](https://aclanthology.org/2026.emnlp-demos.60/) (Vyas et al., EMNLP 2026)
ACL
- Mayank Vyas, Shiven Agarwal, Prisha Nag, Ishita Rajesh Sharma, Abhijit Chakraborty, and Vivek Gupta. 2026. SentinelEdge: A Lightweight, Streaming, Auditable Scam-Call Detection System for the Edge. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 625–638, Budapest, Hungary. Association for Computational Linguistics.