2 citations · 4 across the 12 of their papers we have counts for
12 papers
Assessing Socio-Cyber Vulnerability Using Survey and Social Media Data
Shutonu Mitra, Qi Zhang, Tomas Neguyen +6
The rapid growth of social media participation has increased exposure to socially engineered cyber threats (e.g., phishing, romance fraud, and tech-support scams), yet prevailing a…
DeepSAGE: Stage-Aware Reinforcement Learning for Structured CBT Counseling Dialogue
Qi Zhang, Heajun An, Prakriti Dumaru +4
Large Language Model (LLM)-based counseling agents can generate fluent and supportive responses, but they often lack the structured, goal-directed progression required to conduct a…
CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
Heajun An, Qi Zhang, Vedanth Achanta +1
Large language models (LLMs) are increasingly embedded in adolescent digital environments, mediating information seeking, advice, and emotionally sensitive interactions. Yet existi…
From Vulnerable to Resilient: Examining Parent and Teen Perceptions on How to Respond to Unwanted Cybergrooming Advances
Xinyi Zhang, Mamtaj Akter, Heajun An +6
Cybergrooming is a form of online abuse that threatens teens' mental health and physical safety. Yet, most prior work has focused on detecting perpetrators' behaviors, leaving a li…
Grounded but Misleading: Evaluating Semantic Alignment in AI-Generated Security Explanations
Heajun An, Connor Ng, Sandesh Sharma Dulal +2
Online scams increasingly leverage fluent and context-aware social engineering strategies, creating growing demand for AI systems that explain why a message may be risky. However,…
Scam Shield: Multi-Model Voting and Fine-Tuned LLMs Against Adversarial Attacks
Chen-Wei Chang, Shailik Sarkar, Hossein Salemi +7
Scam detection remains a critical challenge in cybersecurity as adversaries craft messages that evade automated filters. We propose a Hierarchical Scam Detection System (HSDS) that…
LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models
Minqian Liu, Zhiyang Xu, Xinyi Zhang +8
Recent advancements in Large Language Models (LLMs) have enabled them to approach human-level persuasion capabilities. However, such potential also raises concerns about the safety…
SCVI: Bridging Social and Cyber Dimensions for Comprehensive Vulnerability Assessment
Shutonu Mitra, Tomas Neguyen, Qi Zhang +8
The rise of cyber threats on social media platforms necessitates advanced metrics to assess and mitigate social cyber vulnerabilities. This paper presents the Social Cyber Vulnerab…
Toward Integrated Solutions: A Systematic Interdisciplinary Review of Cybergrooming Research
Heajun An, Marcos Silva, Qi Zhang +8
Cybergrooming exploits minors through online trust-building, yet research remains fragmented, limiting holistic prevention. Social sciences focus on behavioral insights, while comp…
Exposing LLM Vulnerabilities: Adversarial Scam Detection and Performance
Chen-Wei Chang, Shailik Sarkar, Shutonu Mitra +7
Can we trust Large Language Models (LLMs) to accurately predict scam? This paper investigates the vulnerabilities of LLMs when facing adversarial scam messages for the task of scam…
Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models
Mohammad Beigi, Sijia Wang, Ying Shen +9
In recent years, Large Language Models (LLMs) have become fundamental to a broad spectrum of artificial intelligence applications. As the use of LLMs expands, precisely estimating…
Generating A Crowdsourced Conversation Dataset to Combat Cybergrooming
Xinyi Zhang, Pamela J. Wisniewski, Jin-hee Cho +2
Cybergrooming emerges as a growing threat to adolescent safety and mental health. One way to combat cybergrooming is to leverage predictive artificial intelligence (AI) to detect p…