Call for Papers

Research on Generative AI and accepted papers appear in IEEE proceedings and IEEE Xplore.

Full papers only, up to six pages—see guidelines for the $50 per-page overage policy and IEEE formatting.

Submit your paperSubmission guidelines

Call for papers

10 research tracks

10 IEEE-aligned tracks cover model risks, systems, and assurance. Expand a track for focus areas, then choose the best fit in EasyChair.

Submit on EasyChairSubmission guidelines

Research on using Generative models to model adversaries, enrich threat intelligence, and simulate attacks and defenses in realistic but controlled settings.

Focus areas

Synthetic attack narratives and TTP emulation
LLM-assisted malware and phishing analysis
Purple-team and tabletop automation
Threat-hunting copilots and knowledge extraction
Benchmarks for intel quality and simulation fidelity
Safety and disclosure for offensive-security research

Attacks and defenses on Generative systems-prompt injection, jailbreaks, data and model poisoning, evasion, and certified or evaluated robustness under adversarial pressure.

Focus areas

Prompt injection, jailbreaks, and tool-use abuse
Training-time poisoning and backdoors in Generative models
Robustness metrics and red-team evaluation pipelines
Detection and mitigation at inference and serving time
Membership and extraction risks for Generative models
Formal or empirical robustness guarantees where applicable

Secure-by-design use of Generative AI in SDLC, CI/CD, and code generation-SAST/DAST augmentation, patch suggestion, supply-chain-aware tooling, and human-in-the-loop review.

Focus areas

Secure code generation and vulnerability-aware assistants
DevSecOps integration and policy gates
SBOM, dependency risk, and provenance for ML-generated code
Human review workflows and accountability
Evaluation of security claims for coding copilots
Secrets handling and unsafe-pattern suppression

Generative AI applied to industrial control, IoT, and cyber-physical systems: anomaly explanation, scenario generation, digital twins, and safety- and timing-aware deployment.

Focus areas

ICS/SCADA and OT-aware Generative models
IoT firmware and configuration risk analysis
Simulation and test-case generation for CPS
Safety constraints and fail-safe behavior
Edge deployment and resource-limited inference
Regulatory and sector-specific assurance

Intersection of Generative methods with quantum and post-quantum contexts: secure protocols, QML-assisted modeling, and analysis of threats and opportunities as quantum capabilities evolve.

Focus areas

Post-quantum cryptography and AI-assisted cryptanalysis (ethical scope)
Quantum machine learning for security-relevant tasks
Hybrid classical–quantum pipelines and threat models
Key management and entropy in ML workloads
Benchmarking and reproducibility for QML security papers
Responsible disclosure for cryptographic findings

Synthetic data generation, differential privacy, federated and distributed training of Generative models, and techniques that balance utility with confidentiality and compliance.

Focus areas

High-fidelity synthetic datasets with privacy budgets
Federated learning for Generative models
Differential privacy during training or inference
Membership inference and reconstruction risks
Federated analytics governance and secure aggregation
Compliance-oriented evaluation (e.g., data minimization)

Generative approaches for secure protocols, network operations, SDN/NFV, and configuration: traffic analysis, policy synthesis, incident narration, and resilient infrastructure design.

Focus areas

Policy and configuration generation for SDN/NFV
LLM-assisted NOC/SOC playbooks and runbooks
Encrypted traffic analysis and anomaly explanation
Zero-trust and microsegmentation with AI assistance
5G and modern WAN security use cases
Verification of generated network artifacts

How humans and Generative systems collaborate in security workflows; organizational, legal, and societal impacts; governance, documentation, and oversight of deployed AI.

Focus areas

Workflow design for analyst–model teaming
Accountability, audit trails, and role clarity
Bias, fairness, and stakeholder impact in security tools
Standards, procurement, and third-party risk
Regulatory alignment and cross-border data issues
Usable security and operator trust in Generative UIs

Using Generative models to expand red-team coverage, discover attack surfaces, and automate defensive tasks-always with clear ethical boundaries and safe harbor for research.

Focus areas

Automated attack-graph and surface exploration
Fuzzing, payload, and scenario generation
Blue-team detection-rule and playbook synthesis
Metrics for coverage vs. harm and false positives
Human oversight and kill switches in automation
Responsible limits on weaponization and publication

Multi-step agents, tool use, memory, and autonomy in security-sensitive settings: containment, least privilege, monitoring, and evaluation of long-horizon agent behavior.

Focus areas

Sandboxing and capability models for agents
Planning, memory, and tool chains under adversarial users
Monitoring, logging, and incident response for agent fleets
Evaluation harnesses for autonomous security tasks
Multi-agent coordination and escalation policies
Deployment patterns for regulated environments

How submission works

From upload to IEEE proceedings

One transparent path: prepare your manuscript, pass peer review, then ship a camera-ready version for the official record.

1
Submit on EasyChair
Upload an anonymized PDF in the official template. Pick the research track that best matches your contribution.
2
Double-blind review
The TPC evaluates novelty, rigor, and relevance to secure Generative AI. Reviewers do not see author identities.
3
Notification & revisions
Accept, reject, or conditional decisions arrive on the published schedule. Address meta-reviews where requested.
4
Camera-ready & IEEE
Final PDFs use the IEEE proceedings format. Accepted papers are published and indexed in IEEE Xplore.