Poster Papers
Young Choi and Paul Hong
A Comparative Analysis of Global AI Safety Perspectives:Toward an Integrated Cybersecurity-Oriented AI SafetyFramework
Rupinder Pal Singh
The UNICORN Framework: A Multi-Dimensional Methodology for
Evaluating Guardrail Robustness in Enterprise Large
Language Model Assistants
Paul Hong, Young B. Choi, and David W. Hwang
Title: Designing Secure Generative AI for Global Supply Chains: Governance-by-Design for Trustworthy Deployment
Aahana Sharma, Antoine Si and Mohammad Iftekhar Husain
Usability and Trust in Cloud Encryption: Experimental
Evaluation of AWS and Related Cloud Platforms
Jeevan Reji and Sanjith Velusamy
The IPv6 Blind Spot: Security Assessment of Dual-Stack VPN Vulnerabilities
​
​
Gulnara Chunareva
Poster: A Lightweight and Scalable Python Framework for Early Anomaly Detection in Security Event Logs
Kanza Fatima, Nan-I Wu, Cheng-Ying Yang and Min-Shiang Hwang
Enhancing Implicit Neural Representation-Based Steganography Using Adaptive Perturbation and Adversarial Training
Aayush Joshi and Dongfeng Fang
Towards Transparent NIDS: An xLSTM-Based Explainable Architecture
Eman Naseerkhan, Meghana Indukuri, Joshua Rose, Martin Tran, and Younghee Park
Reinforcement Learning-Based Strategies for Improving CAPTCHAs
Christopher Yoeurng, Aras Janusonis, Jason Jelincic and
Dongfeng Fang
Exploring the Minimization of Perturbations in Adversarial
Example Generation Against ML-Based NIDS
Taya Ambrose, Sergio Valderrama, Álvaro Cárdenas, and Younghee Park
Poster: DART - Data Augmentation of Rare ATT&CK Techniques
Using LLM Agents
Shanaya Anna Varkey, Shaunak Galvankar and Sean Choi
Fine-tuning Large Language Models via Reinforcement Learning with Verifiable Rewards for Congestion Control
Arjun Sudheer, Jason Kim and Younghee Park
Least Significant Bit Steganography Detection and Analysis Using Large Language Models for Digital Forensics
Haowen Xu, Tianya Zhao, Xuyu Wang, Jun Dai, Xiaoyan Sun
Eavesdropping on the Wrist: Inferring User Behavior from Smartwatch EM Emissions
Tran Ngoc Bao Huynh, Ting Xu, Yinxin Wan, Jun Dai, Xiaoyan Sun
Optimizing IoT Cross-rule Vulnerability Detection through Reinforcement Learning-Based Fuzzing
Kaiman Zeng, Zahra Ghausi, Nina Tkachuk, Kevin Davood,
Bryant Hipolito, and Esteban Verdin
Poster: Rethinking Intrusion Detection Evaluation: The Impact of Cross-Scenario Leakage