Join us at the SECAI 2026 workshop (in conjunction with ESORICS 2026), where we will delve into the impact of Artificial Intelligence (AI) on cybersecurity. AI is transforming various fields, including cybersecurity, where it has been used with great success to enhance the security of networks, systems, and devices. However, the benefits of AI come with new concerns such as safety and ethics, privacy and data protection, data quality, and adversarial attacks that exploit vulnerabilities in AI systems. Moreover, the use of AI can lead to more complex attacks, triggering an AI arms race between attackers and defenders.

To address these challenges and effectively utilise AI for cybersecurity, innovative ideas and effective approaches need to be explored. The SECAI 2026 workshop provides a unique forum for researchers from academia and industry to exchange and discuss new scientific contributions, current accomplishments, and open challenges in this research area. The workshop focuses on three critical research areas that intersect with AI and security:

• AI for security - studies exploring the use of AI techniques to enhance the security of systems and networks
• Malicious use of AI – studies examining how advances in AI create new threats and expand the threat landscape
• Security for AI – studies investigating vulnerabilities in AI algorithms and AI-enabled systems, and approaches to protect them

All papers accepted for SECAI 2026 shall be published in LNCS by Springer. Join us for an exciting and informative workshop at the intersection of AI and cybersecurity.

Submission Guidelines

All papers must be original and not simultaneously submitted to another journal or conference. The following paper categories are welcome.

• Long Papers: These should be at most 16 pages (using 10-point font), excluding the bibliography and well-marked appendices, and at most 20 pages total. Papers should present original research work.
• Short Papers: These should be at most 8 pages (using 10-point font), excluding the bibliography and well-marked appendices, and at most 10 pages total. Papers can present works in progress, descriptions of available datasets, and data collection efforts.

List of Topics

• Attacks on AI and AI-based systems
• AI-enabled attacks and mitigation (e.g., attacker use of AI for automation; scaling, and exploit development)
• Vulnerability assessment of AI and related technologies
• Secure and privacy-preserving AI algorithms and protocols
• Trustworthy and governable AI for cybersecurity (e.g., trust & accountability; explainability; sovereignty & governance; ethical/societal aspects)
• LLM security and robustness
• LLMs for cybersecurity
• AI-assisted attack detection, monitoring, and malware analysis (e.g., anomaly/intrusion detection; malware detection/classification; behavioural analysis)
• AI-assisted forensics and incident response
• AI-assisted cyber threat intelligence and analytics
• AI-assisted authentication and access control
• AI for cryptography and cryptanalysis
• AI for secure software engineering
• AI-assisted security for cloud and big-data environments
• AI-assisted security for cyber-physical and embedded domains (e.g., IoT, CPS, smart grids & digital twins, automotive)
• AI for blockchain security
• AI for fraud detection
• AI for online harms and platform security (e.g., web & social media security; phishing; mis/disinformation; deepfakes)
• Security enhancement in assistive technologies with AI
• Agentic AI security, safety, and governance (e.g., tool-use security; prompt injection; memory poisoning; multi-agent risks; monitoring, containment, human oversight)
• Human factors in AI for security

Committees

Visit the workshop website for details.

Venue

The workshop will be held in conjunction with ESORICS 2026 at Sapienza University of Rome, Main Campus, Città Universitaria, Piazzale Aldo Moro 5, 00185 Rome, Italy.

Contact

All questions about submissions should be emailed to secai.workshop@gmail.com or visit https://sites.google.com/view/secai2026/call-for-papers