Workshop on Secure and Safe AI Agents for Big Data Infrastructures

Our workshop encourages research submissions including (but not limited to) the following list of topics:

• Access Control for AI Agents
• AI Agents for automating infrastructure tasks (e.g., anomaly detection, incident remediation, supply chain)
• AI Agents for malware detection
• Benchmarking for AI Agents deployed in Big Data Infrastructure Systems
• Compliance and Regulations for AI Agents
• Explainability for AI Agents
• Guardrails for AI Agents
• Information Flow Control for AI Agents
• Robustness for AI Agents (e.g., noise, fault tolerance, adversarial attacks)
• Security Architectures for distributed AI Agents
• Execution trace analysis for trustworthy AI Agents

Authors are invited to submit either of the following:

• Full-length research papers up to 10 pages
• Short papers up to 4 pages

Submissions to the workshop must be in PDF and should follow the IEEE BigData paper formatting and single-blind review policy (see link for more information). All accepted submissions will be included in the conference proceedings of IEEE BigData.
To submit a paper, please access the following submission link.