@inproceedings{pavlich-etal-2025-beyond,
title = "Beyond Text-to-{SQL} for {I}o{T} Defense: A Comprehensive Framework for Querying and Classifying {I}o{T} Threats",
author = "Pavlich, Ryan and
Ebadi, Nima and
Tarbell, Richard and
Linares, Billy and
Tan, Adrian and
Humphreys, Rachael and
Das, Jayanta and
Ghandiparsi, Rambod and
Haley, Hannah and
George, Jerris and
Slavin, Rocky and
Choo, Kim-Kwang Raymond and
Dietrich, Glenn and
Rios, Anthony",
editor = "Cao, Trista and
Das, Anubrata and
Kumarage, Tharindu and
Wan, Yixin and
Krishna, Satyapriya and
Mehrabi, Ninareh and
Dhamala, Jwala and
Ramakrishna, Anil and
Galystan, Aram and
Kumar, Anoop and
Gupta, Rahul and
Chang, Kai-Wei",
booktitle = "Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.trustnlp-main.1/",
doi = "10.18653/v1/2025.trustnlp-main.1",
pages = "1--12",
ISBN = "979-8-89176-233-6",
abstract = "Recognizing the promise of natural language interfaces to databases, prior studies have emphasized the development of text-to-SQL systems. Existing research has generally focused on generating SQL statements from text queries, and the broader challenge lies in inferring new information about the returned data. Our research makes two major contributions to address this gap. First, we introduce a novel Internet-of-Things (IoT) text-to-SQL dataset comprising 10,985 text-SQL pairs and 239,398 rows of network traffic activity. The dataset contains additional query types limited in prior text-to-SQL datasets, notably, temporal-related queries. Our dataset is sourced from a smart building{'}s IoT ecosystem exploring sensor read and network traffic data. Second, our dataset allows two-stage processing, where the returned data (network traffic) from a generated SQL can be categorized as malicious or not. Our results show that joint training to query and infer information about the data improves overall text-to-SQL performance, nearly matching that of substantially larger models. We also show that current large language models (e.g., GPT3.5) struggle to infer new information about returned data (i.e., they are bad at tabular data understanding), thus our dataset provides a novel test bed for integrating complex domain-specific reasoning into LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pavlich-etal-2025-beyond">
<titleInfo>
<title>Beyond Text-to-SQL for IoT Defense: A Comprehensive Framework for Querying and Classifying IoT Threats</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Pavlich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nima</namePart>
<namePart type="family">Ebadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Tarbell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Billy</namePart>
<namePart type="family">Linares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachael</namePart>
<namePart type="family">Humphreys</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jayanta</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rambod</namePart>
<namePart type="family">Ghandiparsi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Haley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jerris</namePart>
<namePart type="family">George</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rocky</namePart>
<namePart type="family">Slavin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kim-Kwang</namePart>
<namePart type="given">Raymond</namePart>
<namePart type="family">Choo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Glenn</namePart>
<namePart type="family">Dietrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Rios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trista</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anubrata</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Kumarage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satyapriya</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ninareh</namePart>
<namePart type="family">Mehrabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jwala</namePart>
<namePart type="family">Dhamala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anil</namePart>
<namePart type="family">Ramakrishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aram</namePart>
<namePart type="family">Galystan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-233-6</identifier>
</relatedItem>
<abstract>Recognizing the promise of natural language interfaces to databases, prior studies have emphasized the development of text-to-SQL systems. Existing research has generally focused on generating SQL statements from text queries, and the broader challenge lies in inferring new information about the returned data. Our research makes two major contributions to address this gap. First, we introduce a novel Internet-of-Things (IoT) text-to-SQL dataset comprising 10,985 text-SQL pairs and 239,398 rows of network traffic activity. The dataset contains additional query types limited in prior text-to-SQL datasets, notably, temporal-related queries. Our dataset is sourced from a smart building’s IoT ecosystem exploring sensor read and network traffic data. Second, our dataset allows two-stage processing, where the returned data (network traffic) from a generated SQL can be categorized as malicious or not. Our results show that joint training to query and infer information about the data improves overall text-to-SQL performance, nearly matching that of substantially larger models. We also show that current large language models (e.g., GPT3.5) struggle to infer new information about returned data (i.e., they are bad at tabular data understanding), thus our dataset provides a novel test bed for integrating complex domain-specific reasoning into LLMs.</abstract>
<identifier type="citekey">pavlich-etal-2025-beyond</identifier>
<identifier type="doi">10.18653/v1/2025.trustnlp-main.1</identifier>
<location>
<url>https://aclanthology.org/2025.trustnlp-main.1/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>1</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Text-to-SQL for IoT Defense: A Comprehensive Framework for Querying and Classifying IoT Threats
%A Pavlich, Ryan
%A Ebadi, Nima
%A Tarbell, Richard
%A Linares, Billy
%A Tan, Adrian
%A Humphreys, Rachael
%A Das, Jayanta
%A Ghandiparsi, Rambod
%A Haley, Hannah
%A George, Jerris
%A Slavin, Rocky
%A Choo, Kim-Kwang Raymond
%A Dietrich, Glenn
%A Rios, Anthony
%Y Cao, Trista
%Y Das, Anubrata
%Y Kumarage, Tharindu
%Y Wan, Yixin
%Y Krishna, Satyapriya
%Y Mehrabi, Ninareh
%Y Dhamala, Jwala
%Y Ramakrishna, Anil
%Y Galystan, Aram
%Y Kumar, Anoop
%Y Gupta, Rahul
%Y Chang, Kai-Wei
%S Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-233-6
%F pavlich-etal-2025-beyond
%X Recognizing the promise of natural language interfaces to databases, prior studies have emphasized the development of text-to-SQL systems. Existing research has generally focused on generating SQL statements from text queries, and the broader challenge lies in inferring new information about the returned data. Our research makes two major contributions to address this gap. First, we introduce a novel Internet-of-Things (IoT) text-to-SQL dataset comprising 10,985 text-SQL pairs and 239,398 rows of network traffic activity. The dataset contains additional query types limited in prior text-to-SQL datasets, notably, temporal-related queries. Our dataset is sourced from a smart building’s IoT ecosystem exploring sensor read and network traffic data. Second, our dataset allows two-stage processing, where the returned data (network traffic) from a generated SQL can be categorized as malicious or not. Our results show that joint training to query and infer information about the data improves overall text-to-SQL performance, nearly matching that of substantially larger models. We also show that current large language models (e.g., GPT3.5) struggle to infer new information about returned data (i.e., they are bad at tabular data understanding), thus our dataset provides a novel test bed for integrating complex domain-specific reasoning into LLMs.
%R 10.18653/v1/2025.trustnlp-main.1
%U https://aclanthology.org/2025.trustnlp-main.1/
%U https://doi.org/10.18653/v1/2025.trustnlp-main.1
%P 1-12
Markdown (Informal)
[Beyond Text-to-SQL for IoT Defense: A Comprehensive Framework for Querying and Classifying IoT Threats](https://aclanthology.org/2025.trustnlp-main.1/) (Pavlich et al., TrustNLP 2025)
ACL
- Ryan Pavlich, Nima Ebadi, Richard Tarbell, Billy Linares, Adrian Tan, Rachael Humphreys, Jayanta Das, Rambod Ghandiparsi, Hannah Haley, Jerris George, Rocky Slavin, Kim-Kwang Raymond Choo, Glenn Dietrich, and Anthony Rios. 2025. Beyond Text-to-SQL for IoT Defense: A Comprehensive Framework for Querying and Classifying IoT Threats. In Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025), pages 1–12, Albuquerque, New Mexico. Association for Computational Linguistics.