We invite AI researchers and practitioners across different disciplines and knowledge backgrounds to submit contributions dealing with the following (or related) topics:

• Deceptive and Malicious Uses of AI

  • • • AI-generated misinformation, disinformation, deepfakes, and synthetic media

      • Fraud, impersonation, scams, and AI-enabled social engineering

      • Personalized persuasion, manipulation, and deceptive AI interactions

      • Automated generation and dissemination of harmful or misleading content

• Security of Generative and Agentic AI

  • • • Jailbreaks, direct and indirect prompt injection, and goal hijacking

      • Tool misuse, memory poisoning, excessive agency, and unsafe autonomous behavior

      • Attacks exploiting interactions between agents, users, Web content, and external services

      • Security and privacy risks in multi-agent systems and agent-to-agent communication

• Identity, Authority, and Control for AI Agents

  • • • Agent identity, authentication, authorization, and delegated authority

      • Least-privilege access and secure interaction with tools, APIs, and Web services

      • Provenance, traceability, and accountability for AI-generated content and actions

      • Human oversight, interruption, rollback, and mechanisms for maintaining meaningful user control

• Detection, Evaluation, and Mitigation

  • • • Detection of AI-generated deception, misinformation, impersonation, and malicious behavior

      • Adversarial testing, red teaming, threat modeling, and risk assessment

      • Benchmarks, datasets, scenario libraries, and reproducible evaluation methodologies

      • Monitoring, auditing, incident analysis, and post-deployment evaluation

      • Robustness, uncertainty, interpretability, and evaluation of AI safeguards

• Privacy, Trust, and Human–AI Interaction

  • • • Privacy leakage, sensitive-data exposure, and inference attacks

      • Overreliance on AI and loss of human autonomy or control

      • Trust calibration and deceptive or manipulative human–AI interactions

      • Bias, discrimination, accessibility, and unequal impacts of AI systems

      • Effects of AI-generated and AI-mediated content on online information ecosystems

• Responsible AI and Governance

  • • • Transparency, accountability, provenance, and auditing mechanisms

      • Governance of autonomous and semi-autonomous AI systems

      • Legal and ethical implications of AI-generated content and autonomous actions

      • Responsible deployment of AI in security-sensitive and high-risk domains

      • Technical and organizational approaches to trustworthy AI deployment

We welcome submissions spanning the full range of theoretical and applied work, including user research, methods, datasets, tools, simulations, demos, and practical evaluations. 

Submission Details