| |||||||||||||||
HICSS AI4Cyber and Cyber4AI 2025 : HICSS 58 Mini-Track: Collaborative AI, LLMs, & Cybersecurity - Cybersecurity in the Age of Artificial Intelligence, AI for Cybersecurity, and Cybersecurity for AI | |||||||||||||||
Link: http://www.azsecure-hicss.org/home.html | |||||||||||||||
| |||||||||||||||
Call For Papers | |||||||||||||||
HICSS-58 Mini-Track CFP
Collaborative AI, LLMs, & Cybersecurity - Cybersecurity in the Age of Artificial Intelligence, AI for Cybersecurity, and Cybersecurity for AI Track: Collaboration Systems and Technologies Track Site: https://hicss.hawaii.edu/tracks-58/collaboration-systems-and-technologies/#cybersecurity-in-the-age-of-artificial-intelligence-ai-for-cybersecurity-and-cybersecurity-for-ai-minitrack Submission Deadline: June 15th, 2024 (Submission Link Now Open) Submission Link: https://hicss-submissions.org/submissions/new Topics and research areas can include, but are not limited to: + Novel applications of Artificial Intelligence, Machine Learning, LLMs, and Deep Learning in Cybersecurity as they pertain to multi-user/multi-organizational collaborative domains and/or systems. + Adversarial AI Applications in Cybersecurity that collaboratively span organizations or apply to collaborative systems (i.e., malware, phishing, LLMs, or any applicable threat/identification domain). + Protecting AI that is used collaboratively (i.e., LLMs, shared data sets, shared models, shared applications) or spans collaborative domains from cybersecurity threats (i.e., adversarial examples, trojans, model inversion). + Using AI to protect AI in any appropriate wide-reaching setting. + Novel Collaboration approaches to leveraging and protecting AI in the cybersecurity domain. + Sharing/disseminating tools, techniques, and applications of AI in Cybersecurity and Cybersecurity for AI that apply to the overarching theme of this mini-track. Examples: + Modern LLM’s: Results Integrity, Prompt Security, Prompt Attach Detection, Result Error Detection, Dangerous Output Detection, Hallucination Detection, Prompt Jailbreaking. + Cybersecurity Domain Data Analytics: Leveraging AI to analyze any of the myriad datasets in the cybersecurity domain such as log files, network traffic, data at rest, etc., for legitimate cybersecurity purposes. + Vulnerability Assessment: Scanning Code for Vulnerabilities using AI / LLMS; Tracking and identifying / labeling code, containers, or repositories based on their vulnerabilities and/or vulnerability persistence over time and forks. + Secure Coding: Securing existing code or automatically generating new secure code either from scratch or by generating secure code clones. + Remediation: Effectively and efficiently identifying appropriate remediations for detected vulnerabilities from the large amounts of existing data. + Model Security for AI and LLM Models: Identifying models that have been perturbed, perturbing models to create model perturbation detection technologies, detecting the effect of model perturbations, identifying bias in models, identifying errors in models, removing perturbations from models. + Security for AI and LLM Datasets: Insuring distributed dataset integrity, detecting perturbations in datasets, identifying the effects of dataset perturbations, removing perturbations from datasets. + Attack Detection: Analyzing real-time data streams to identify immediate attacks as they occur. Name, affiliation, and contact information of Mini-Track Chairs: Hsinchun Chen UA Regents' Professor of MIS Management Information Systems University of Arizona hsinchun@email.arizona.edu Mark Patton (Primary Contact) Lecturer Management Information Systems University of Arizona mpatton@email.arizon.edu o: 520-626-8614 m: 520-250-4763 McClelland Hall 430 1130 E. Helen Street Tucson Arizona 85721 Sagar Samtani Assistant Professor and Weimer Faculty Fellow Department of Operations and Decision Technologies Indiana University ssamtani@iu.edu Hongyi Zhu Assistant Professor Department of Information Systems and Cyber Security Alvarez College of Business University of Texas at San Antonio hongyi.zhu@utsa.edu |
|