Deadline in 15 days! Call for Papers: AISS 2026, December 13-15, Hefei, China
| | Call for papers The 1st International Conference on Artificial Intelligence Safety and Security (AISS 2026) Hefei, China | December 13-15, 2026 Held in conjunction with AI3T 2026 Theme: Building Trustworthy, Safe, and Secure Intelligence | | Introduction The 1st International Conference on Artificial Intelligence Safety and Security (AISS 2026) will convene in Hefei, China, held in conjunction with the 1st International Conference on AI Infrastructure and Interconnect Technologies (AI3T 2026). As increasingly autonomous AI systems enter physical and social environments, AISS 2026 will address risks ranging from unpredictable behavior and manipulated agents to compromised training pipelines and failures with real-world consequences. Bringing together researchers, industry practitioners, and policymakers, the conference will showcase work on data integrity, model alignment, infrastructure protection, evaluation, red teaming, standards, and governance. Join a global community to advance AI systems that can be trusted and deployed responsibly at scale! | Scope and Topics | | We solicit original, high-quality research papers and practical experience reports on all aspects of AI safety and security. Topics of interest include, but are not limited to: Foundations of Trustworthy and Safe AI • Robustness, generalization, and reliability of AI models under distribution shift • Uncertainty quantification, calibration, and out-of-distribution detection • Interpretability, explainability, and mechanistic understanding of model behavior • Alignment, value specification, and controllable AI system design Safety of Foundation Models and Agentic AI • Safety evaluation, red teaming, and adversarial testing of large language and multimodal models • Jailbreaking, prompt injection, and defense for tool-using and agentic systems • Hallucination detection, factual grounding, and truthfulness in generative models • Safety of long-horizon autonomous agents, multi-agent systems, and AI workflows Security of AI Systems and AI Infrastructure • Attacks on the AI lifecycle: data poisoning, backdoors, model extraction, and membership inference • Security of training and inference infrastructure, accelerators, and AI accelerators supply chain • Model and data supply-chain security, provenance, and integrity attestation • Side-channel, hardware, and cross-tenant leakage in shared AI infrastructure Privacy-Preserving and Confidential AI • Differential privacy, federated learning security, and privacy-preserving training • Confidential computing, trusted execution environments, and secure enclaves for AI • Machine unlearning, data rights, and training-data attribution • Privacy risks of multimodal and embodied systems collecting real-world data Safety and Security of Embodied and Cyber-Physical AI • Safety assurance and fail-safe behavior for robots, autonomous vehicles, and embodied agents • Security of networked robots, teleoperation, and vehicle-to-everything systems • Robustness of world models and embodied policies to sensing, actuation, and network attacks • Formal verification, runtime monitoring, and safety envelopes for physical AI systems AI Safety Evaluation, Benchmarking, and Assurance • Benchmarks, metrics, and testbeds for AI safety, security, and robustness • Assurance cases, safety cases, and audit methodologies for AI systems • Incident reporting, failure taxonomies, and post-deployment monitoring • Reproducible evaluation of defenses and responsible disclosure practices Governance, Standards, and Compliance • AI governance frameworks, risk management, and regulatory compliance • International and national standards, certification, and conformity assessment • Liability, accountability, and human oversight of autonomous AI systems • Safety and security practices in industrial deployment and public-sector adoption AI for Security and Defense • Machine learning for intrusion, malware, fraud, and anomaly detection • AI-assisted vulnerability discovery, threat intelligence, and security operations • Autonomous cyber defense and AI-driven incident response • Adversarial machine learning: attack generation and certified defenses | | Important dates | | Full Paper Submission Deadline: October 31, 2026 Author Notification: November 15, 2026 Camera Ready Submission: November 30, 2026 Registration Deadline: November 30, 2026 | | Organizing committee | | General Chairs: Jingqiang Lin, University of Science and Technology of China, China Yongqiang Lyu, Tsinghua University, China Xianjun Deng, Huazhong University of Science and Technology, China Program Chairs: Jie Cui, Anhui University, China Meng Li, Hefei University of Technology, China | | Paper submission | | Ø Submitted papers must be original, written in English, and not under consideration for publication elsewhere. All submissions will undergo double-blind peer review. Ø Full Papers: up to 8 pages, with up to 4 additional pages. Short Papers: up to 4 pages, with up to 4 additional pages. Posters: up to 2 pages, with up to 2 additional pages. Additional pages are subject to extra-page fees. Ø Manuscript format: IEEE Computer Society Proceedings format (two columns, single-spaced, 10-point font). Ø Accepted papers can be presented in oral, poster, or online format. Ø Registration fees must be paid before uploading the final, publication-ready version of the paper. The final PDF must pass the IEEE PDF eXpress compliance check before final submission. | | Publication | | All papers will be reviewed by three experts. After a careful reviewing process, all accepted papers with proper registration and presentation will be published in IEEE Xplore, and will be submitted to EI Compendex and Scopus for indexing. | | Website | | Ø AISS 2026 Homepage: http://aiss.ieee-aiconf.cn/ Ø Submission Website: http://aiss.hotcrp.ieee-aiconf.cn/ | | Contact | | Ø For any inquiries regarding the conference, please contact us at: secretary@ieee-aiconf.cn |
participants (1)
-
Zhiyao Liu