6 papers
Taming Silent Failures: A Framework for Verifiable AI Reliability
Guan-Yan Yang, Farn Wang
The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outpu…
ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test
Guan-Yan Yang, Tzu-Yu Cheng, Ya-Wen Teng +2
The integration of Large Language Models (LLMs) into computer applications has introduced transformative capabilities but also significant security challenges. Existing safety alig…
GNN-enhanced Traffic Anomaly Detection for Next-Generation SDN-Enabled Consumer Electronics
Guan-Yan Yang, Farn Wang, Kuo-Hui Yeh
Consumer electronics (CE) connected to the Internet of Things are susceptible to various attacks, including DDoS and web-based threats, which can compromise their functionality and…
TPSQLi: Test Prioritization for SQL Injection Vulnerability Detection in Web Applications
Guan-Yan Yang, Farn Wang, You-Zong Gu +4
The rapid proliferation of network applications has led to a significant increase in network attacks. According to the OWASP Top 10 Projects report released in 2021, injection atta…
Enhancing Resilience for IoE: A Perspective of Networking-Level Safeguard
Guan-Yan Yang, Jui-Ning Chen, Farn Wang +1
The Internet of Energy (IoE) integrates IoT-driven digital communication with power grids to enable efficient and sustainable energy systems. Still, its interconnectivity exposes c…
Automated Vulnerability Detection Using Deep Learning Technique
Guan-Yan Yang, Yi-Heng Ko, Farn Wang +3
Our work explores the utilization of deep learning, specifically leveraging the CodeBERT model, to enhance code security testing for Python applications by detecting SQL injection…