Secure software development with AI

Artificial Intelligence (AI) is transforming the software development lifecycle by enabling intelligent code generation, automated testing, vulnerability detection, code review, and software maintenance. AI-powered development tools, including Large Language Models (LLMs), code assistants, and intelligent DevSecOps platforms, are significantly improving developer productivity and software quality. However, the widespread adoption of AI in software engineering also introduces new security challenges, including AI-generated vulnerable code, insecure code recommendations, software supply chain attacks, prompt injection, model manipulation, intellectual property concerns, and risks associated with AI-assisted development. As organizations increasingly rely on AI throughout the Software Development Life Cycle (SDLC), integrating security into AI-driven development processes has become essential for building resilient and trustworthy software systems.

The International Conference on Cyber Security in Artificial Intelligence (ICCSAI 2027) invites original research contributions on Secure Software Development with AI. This track aims to provide a multidisciplinary forum for researchers, software engineers, cybersecurity professionals, AI experts, DevSecOps practitioners, and industry leaders to present innovative research and practical solutions for developing secure software using AI technologies. Contributions addressing AI-assisted secure coding, intelligent vulnerability detection, secure DevSecOps, automated security testing, software supply chain security, AI governance, and trustworthy AI-assisted software engineering are particularly encouraged.

Subtopics

1. AI-Assisted Secure Software Engineering

  • AI-Assisted Software Development

  • AI for Secure Software Engineering

  • AI-Based Software Design and Architecture

  • AI-Assisted Requirements Engineering

  • AI-Driven Software Quality Assurance

  • Intelligent Software Maintenance

2. Secure Software Development Lifecycle (Secure SDLC)

  • AI-Enabled Secure SDLC

  • Security-by-Design

  • Secure Coding Practices with AI

  • AI for Secure Software Architecture

  • AI-Assisted Secure Code Generation

  • AI for Software Security Reviews

3. AI for Code Analysis and Testing

  • AI-Powered Static Application Security Testing (SAST)

  • AI-Based Dynamic Application Security Testing (DAST)

  • AI-Assisted Interactive Application Security Testing (IAST)

  • AI for Software Composition Analysis (SCA)

  • AI-Based Code Review

  • AI for Unit, Integration, and Regression Testing

  • AI-Assisted Fuzz Testing

4. Vulnerability Detection and Remediation

  • AI-Based Vulnerability Detection

  • Automated Vulnerability Assessment

  • AI-Assisted Patch Generation

  • Vulnerability Prioritization Using AI

  • AI for Secure Bug Detection

  • Common Vulnerabilities and Exposures (CVE) Analysis

5. DevSecOps and Software Supply Chain Security

  • AI-Driven DevSecOps

  • Secure Continuous Integration and Continuous Deployment (CI/CD)

  • AI for Infrastructure-as-Code (IaC) Security

  • Software Supply Chain Security

  • Open-Source Software Security

  • Software Bill of Materials (SBOM) Analysis

  • Dependency and Package Security

6. AI Security in Software Development

  • Security of AI Coding Assistants

  • Secure Large Language Models (LLMs) for Software Development

  • Prompt Injection Attacks on Code Generation Models

  • AI Model Poisoning in Software Development

  • Secure AI APIs and SDKs

  • AI Model Lifecycle Security

7. Cloud-Native and Container Security

  • Secure Cloud-Native Application Development

  • Container Security

  • Kubernetes Security

  • Microservices Security

  • Serverless Application Security

  • API Security with AI

8. Trustworthy AI for Software Security

  • Explainable AI for Secure Software Engineering

  • Trustworthy AI-Assisted Development

  • Responsible AI in Software Engineering

  • AI Governance for Secure Development

  • AI Risk Assessment

  • AI Compliance and Regulatory Requirements

9. Privacy and Data Security

  • Privacy-Preserving Software Development

  • Secure Data Handling in AI Applications

  • Data Privacy in AI-Assisted Development

  • Secure Secrets and Credential Management

  • Encryption and Key Management

  • Secure Logging and Monitoring

10. Formal Verification and Program Analysis

  • Formal Methods for Software Security

  • AI-Assisted Formal Verification

  • Symbolic Execution

  • Program Analysis Using AI

  • Secure Compiler Technologies

  • Runtime Verification

11. Emerging Technologies

  • Generative AI for Secure Coding

  • AI Agents for Software Development

  • Autonomous Secure Software Engineering

  • Blockchain for Software Integrity

  • Quantum-Resistant Software Development

  • Secure Digital Twins

  • Federated AI for Software Engineering

12. Evaluation, Benchmarking, and Applications

  • Security Benchmarking for AI-Generated Code

  • Evaluation of AI Coding Assistants

  • Secure Software Engineering Datasets

  • AI Metrics for Software Security

  • Industrial Case Studies

  • AI-Driven Secure Software Development Frameworks

  • Best Practices for AI-Assisted Secure Development