activity
20242026
collaborators

7 papers

cs.AI2026

From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents

Yuhao Sun, Jiacheng Zhang, Shaanan Cohney +3

LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk catego…

cs.CR2025

Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting

Hua Ma, Ruoxi Sun, Minhui Xue +4

Accurate time-series forecasting is increasingly critical for planning and operations in low-carbon power systems. Emerging time-series large language models (TS-LLMs) now deliver…

cs.CR2025

From Description to Detection: LLM based Extendable O-RAN Compliant Blind DoS Detection in 5G and Beyond

Thusitha Dayaratne, Ngoc Duy Pham, Viet Vo +5

The quality and experience of mobile communication have significantly improved with the introduction of 5G, and these improvements are expected to continue beyond the 5G era. Howev…

cs.CR2025

MulVuln: Enhancing Pre-trained LMs with Shared and Language-Specific Knowledge for Multilingual Vulnerability Detection

Van Nguyen, Surya Nepal, Xingliang Yuan +3

Software vulnerabilities (SVs) pose a critical threat to safety-critical systems, driving the adoption of AI-based approaches such as machine learning and deep learning for softwar…

cs.SE2024

SAFE: Advancing Large Language Models in Leveraging Semantic and Syntactic Relationships for Software Vulnerability Detection

Van Nguyen, Surya Nepal, Tingmin Wu +2

Software vulnerabilities (SVs) have emerged as a prevalent and critical concern for safety-critical security systems. This has spurred significant advancements in utilizing AI-base…

cs.CR2024

An Innovative Information Theory-based Approach to Tackle and Enhance The Transparency in Phishing Detection

Van Nguyen, Tingmin Wu, Xingliang Yuan +3

Phishing attacks have become a serious and challenging issue for detection, explanation, and defense. Despite more than a decade of research on phishing, encompassing both technica…