The International Conference on Assured Autonomy (ICAA) plans to address the gap that exists between theory-heavy artificially intelligent autonomous systems and the privacy, security, and safety of their real-world implementations. Advances in machine learning (ML) and artificial intelligence (AI) have shown great promise in algorithms and techniques for automating complex decision-making processes across transportation, robotics, critical infrastructure, and cyber infrastructure domains. Practical implementations of these algorithms require significant systems engineering and integration support for safe, trusted, and assured operations, especially as they integrate with the physical world. This need for assurance is further challenged by AI safety, security, privacy, responsibility, bias, and alignment issues.
The focus of this conference is the: (1) Design of Assured and Safe Systems with AI and Autonomy, (2) Real-world Studies, Deployments and Industry Uses of Assured AI and Autonomy (3) Methods for Testing and Assuring AI and AI-enabled Autonomous Systems, and (4) Security and Privacy of AI and Autonomous Systems, which includes methods to detect, respond, mitigate, and recover resiliently to violations in safety, security, and privacy, and trust.
Topics and types of contributions
ICAA seeks new methodologies and contributions as well as applications and studies of all aspects of AI safety, security, and assurance in autonomous systems. Papers that encourage the discussion and exchange of experimental and theoretical results, novel designs, real-world uses, case studies and works in progress are requested. Both full papers (up to 10 pages) and working papers (up to 4 pages) will be accepted. Topics of interest include (but are not limited to):
Design for Assured and Safe Autonomy
Safe-by-construction methods for autonomous systems
Formally verified AI and autonomy
Neuro-symbolic learning and reasoning for assured, resilient autonomy
Systems that learn and adapt in the field
Sim-to-real transfer for assured AI and autonomy
Runtime assurance and monitoring
-
Safe learning and control for autonomous and AI-enabled systems
-
Real-world studies, uses, and design considerations of AI for autonomous systems
Methods for Testing and Assuring AI and Autonomy
Explainable and interpretable AI-enabled systems
Alignment and safety of AI and autonomous systems
Standards, ethics, and policies for autonomy and AI to meet responsible AI principles
Verification, validation, testing, and assurance of systems with AI and autonomy
Evaluating safety of autonomous systems according to their potential risks and vulnerabilities
Test, evaluation, certification, and assurance of autonomous AI systems
Modeling and simulation, virtual constructive and live testing challenges for AI and autonomous systems
Safety, evaluation, and assurance of human-autonomy teaming
Evaluation and safety of foundation models
Lessons learned from deployments and industrial uses of AI and autonomy
Security and Privacy of AI and Autonomous Systems
Detecting dataset anomalies that lead to autonomous system security and privacy violations
Detecting data poisoning, model poisoning and system attacks
Differential privacy and privacy-preserving learning and generative models
Adversarial attacks on AI and autonomy, and defenses against adversarial attacks
Mitigation and improved resiliency of AI and autonomous systems to various forms of attacks
Engineering trusted autonomous system and AI software architectures
Red-teaming and stress testing of AI-enabled systems to identify vulnerabilities
Real-world studies of security and privacy challenges for AI and autonomy
Paper Format
- Full papers (10 pages)
- Work-in-progress papers (4 pages)
Submission Guidelines
You are invited to submit regular papers (up to ten pages), or working papers (up to four pages), including references. To be considered, papers must be received by the submission deadline.
Submissions must be original work and may not be under submission to another venue at the time of review. Please mark all of your conflicts of interest when submitting your paper. Papers should be in IEEE conference format.
Templates can be found at
https://www.ieee.org/conferences/publishing/templates.html.
Presentation Form
All accepted submissions will be presented at the conference and are planned to be included in an IEEE conference proceedings.
One author of each accepted paper is required to attend the conference and present the paper for it to be included in the proceedings.
Submission Website
All presented papers will be published in the conference proceedings and submitted to the IEEE Xplore Digital Library.
To submit a full length paper or working paper, please go to our EasyChair submission site at:
https://easychair.org/conferences/?conf=icaa24
Supported By
Contact Us
Please send comments and questions to auroraschmidt "at" gmail "dot" com.
