Call For Papers: Special Issue on on Visualization for Secure AI and Cyber Systems

Important Dates

• Submission Deadline: 4 January 2027
• Publication: July 2027

The visual computing community is increasingly called upon to address challenges from the perspective of security in modern cyber systems. On one side, cybersecurity operations, such as network monitoring, intrusion detection, threat hunting, and log analysis, generate vast, complex data that demand interactive visualization for human sensemaking and rapid response. On the other side, the increasing adoption of generative AI technologies, including large language models (LLMs) in cyber environments, introduces novel security concerns, including prompt injection, jailbreak attacks, model provenance, training data poisoning, and adversarial behavior auditing, all of which lack mature visual analytics support. Both share a common need: visualization as a first-class tool to make security problems interpretable, traceable, and actionable.

This special issue invites original contributions on visualization and visual analytics that offer a coherent lens through which both traditional cybersecurity and emerging AI security challenges can be analyzed, communicated, and addressed. We seek papers that treat security analysis as a visual analysis problem and that view visualization as a tool for cyber defense, model auditing, and risk communication. Submissions may come from visualization, visual analytics, human-computer interaction, and security-focused AI/ML communities, provided that visualization or visual analytics constitutes a primary intellectual contribution of the work, rather than serving merely as a secondary or illustrative component of a security system.

We are particularly interested in work that addresses the unique challenges posed by LLMs, including prompt-based attacks, model provenance, and behavioral auditing, and how visualization can make these opaque systems interpretable, accountable, and secure. Topics of interest include, but are not limited to:

• Visualization for cyber-security operations (e.g., network traffic, intrusion detection, threat hunting)
• Conversational visual analytics for cybersecure environments
• Visual analytics for LLM security: prompt injection detection, jailbreak pattern analysis, and model behavior auditing
• Provenance and watermarking visualization for secure visual media workflows
• Interactive systems for adversarial robustness assessment of vision-language models
• Human-in-the-loop interfaces for security sensemaking under LLM-generated threats
• Secure visualization pipelines: integrity, confidentiality, and trust in visual computing systems
• Visualization of LLM training data contamination, poisoning, and backdoor attacks
• Usable security interfaces for non-expert stakeholders in LLM-mediated creative pipelines
• Visualization for agentic AI systems and autonomous agent security workflows
• AI reasoning and provenance visualization for model transparency
• Human-AI collaborative interfaces for cyber defense and threat response
• Trust and security visualization in autonomous agent decision-making pipelines

In addition to research papers, IEEE CG&A invites Perspective and Overview Paper (POP) submissions related to this theme. POP papers may include surveys, tutorials, state-of-the-art reports, or forward-looking perspectives that synthesize knowledge or explore emerging aspects of the CFP theme. For details, visit  CG&A Author Information Page, but please submit your paper to this special issue rather than the regular POP queue.

Submission Guidelines

For author information and guidelines on submission criteria, visit the Author Information Page. Please submit papers through the IEEE Author Portal and be sure to select the special issue or special section name. Manuscripts should not be published or currently submitted for publication elsewhere. Please submit only full papers intended for review, not abstracts.

In addition to submitting your paper to IEEE CG&A you are also encouraged to upload the data related to your paper to IEEE DataPort. IEEE DataPort is IEEE's data platform that supports the storage and publishing of datasets while also providing access to thousands of research datasets. Uploading your dataset to IEEE DataPort will strengthen your paper and will support research reproducibility. Your paper and the dataset can be linked, providing a good opportunity for you to increase the number of citations you receive. Data can be uploaded to IEEE DataPort prior to submitting your paper or concurrent with the paper submission. Thank you!

Guest Editors

• Xumeng Wang (Lead GE), Nankai University, China
• Chris Bryan, Arizona State University, USA
• Aritra Dasgupta, New Jersey Institute of Technology, USA