CFP: 3rd International Workshop on Safety and Security in Multiagent Systems
(SASEMAS '06)
May 8, 2006
To be held in conjunction with AAMAS 2006, Hakodate, Japan
Important Dates
Paper Submission:January 15th, 2006February 1st, 2006 (submission deadline extended by AAMAS)
Notifications: February 19th, 2006
Workshop: May 8th, 2006
Overview
As intelligent autonomous agents and multi-agent systems applications become more pervasive, it becomes increasingly important to understand the risks associated with using these systems. Incorrect or inappropriate agent behaviour can have harmful effects, including financial cost, loss of data, and injury to humans or systems. Thus, security and safety are two central issues when developing and deploying such systems.
In complex and rich environments, such as multiagent system environments, it is often necessary to involve the agents of the system in achieving some of these design goals, by making the goals explicit for the agent itself. For example, the agent must be aware of user-specified safety conditions if it is going to avoid violating them. This often means that an agent needs to be able to identify, assess, and mitigate many of the risks it faces. This is particularly true when the agent is going to be deployed in dangerous environments without immediate user input; for example, command of a spacecraft where communication with mission control involves considerable delays.
Moreover, agents often integrate such activities as deliberately planning to achieve their goals, dynamically reacting to obstacles and opportunities, communicating with other agents to share information and coordinate actions, and learning from and/or adapting to their environments. Because agents are often situated in dynamic environments, these activities are often time-sensitive. These aspects of agents make the process of developing, verifying, and validating safe and secure multiagent systems more difficult than for conventional software systems. New techniques and perspectives are required to assist with the development and deployment of such systems.
Intended Participants
The workshop will present new developments, lessons learned from real world cases, and will provide a forum for the exchange of ideas and discussion on areas related to safety and security of multiagent systems. This workshop will be of interest to researchers and developers of agent systems for a wide range of emerging applications. The workshop will also be of interest to those who use agent technology in safety- and security-critical applications.
Challenge Problems
In order to make many of these issues more concrete, we are introducing a separate competition that will be associated with this workshop. This competition will consist of challenge problems for the design of safe and secure intelligent autonomous agents and multi-agent systems, and will be based on extensions to the RoboCup Rescue Simulation platform.
Additional details will be available shortly at: http://www.sasemas.org/2006/challenge.html
Best Paper Awards
This year, we will be awarding two prizes, one for the best paper and one for the best runner-up paper. The winner of the best paper award will receive a prize of US$100 and the runner-up will receive a US$50 prize.
Student Support
There will be limited support available for students submitting papers.
Publication
Selected papers from the last two year's SASEMAS workshops will appear in a post-proceedings volume published by Springer Verlag in the LNCS/LNAI series. We also intend to have Springer-Verlag publish selected papers from this year's workshop as a post-proceedings LNAI volume.
Formatting guidelines
We encourage submission in Springer Lecture Notes Series format. The length of papers is recommended to be 12 to 15 pages long in this format. See the Springer LNCS home page, http://www.springer.de/comp/lncs/authors.html.
All non-presenting participants should submit a one-page position statement which presents their perspective on safe agents. Position papers from industry participants are especially encouraged.
All submissions must include the author's name(s), affiliation, complete mailing address, phone number, fax number and email address.
Submission procedure:
Paper Submission: February 1st, 2006 (new deadline)
Notifications: February 19th, 2006
Submitted papers must be in PDF or postscript format. Papers may be submitted here. We will require on-line submission of papers through the workshop's site. Automatic submission will be enabled by the end of December 2005.
Position statements from non-presenting workshop participants may be mailed to: workshop06@sasemas.org.
The position papers may be in PDF, postscript, or text format.
Multiple submission policy for papers: Papers that are being submitted to other conferences, whether verbatim or in essence, must reflect this fact on the title page. Papers that do not meet this requirement are subject to rejection without review.
Proposed Topics
This workshop will explore issues related to the development and deployment of "safe and secure agents and multiagent systems".
Relevant topics include, but are not limited to:
Definitions of safety and security for single agents or entire systems.
What does it mean for an agent to be "safe", or to be "secure" and to "behave appropriately"? How can answers to the above questions be lifted to multiagent systems?Verification/validation of agent and multiagent systems.
How can agents, working in complex, open systems, be shown to be "safe" or "secure"? Can a multiagent system, which is composed of "safe" agents, be itself "unsafe"? Can the composition of "secure" agents lead to an "insecure" system?Design, mechanisms and deployment.
What are the tradeoffs between safety/security, and performance? What mechanisms can be used to ensure/improve the safety and/or security of an agent and/or multiagent system; e.g. how can agents be designed for robustness in a given environment?
Do old-style methodologies, formal specification, declarative languages, and user-friendly interfaces have roles to play for agent building environments?User requirements, agent behavior, and trust.
How can the user be made safe from agents performing "risky" actions? How can trust and reputation mechanisms be supported? How can a multiagent society be made safe from its member agents performing "malicious" actions?Autonomy and Autonomous Reasoning.
How can agents reason about their own safety, e.g., determining the types and degrees of dangers inherent in different courses of action.
How can adjustable autonomy be used to ensure agents behave reasonably?Learning/adaptive agents.
How can agents that are self-modifying be shown to be safe and to avoid security related risks? In hostile environments, how can agents learn what is safe and secure to do and what is not?Application areas.
Which application areas would benefit from agent technology but would also be very sensitive to safety or security issues?
Organizing Committee
Program Chairs:
Haralambos Mouratidis
Email: haris@uel.ac.uk
School of Computing and Technology, University of East London
Longbridge Road, RM8 2AS, Dagenham, London, U.K.
Diana Spears
Department of Computer Science, University of Wyoming
Dept. 3315, 1000 E. University Avenue
Laramie, WY 82071, USA
General Chair: Mike Barley
Computer Science Department, University of Auckland, Private Bag 92019
Auckland, New Zealand
Publicity Chair: Amy Unruh
Dept. of Computer Science and Software Engineering, The University of Melbourne
Victoria 3010, Australia
For general information, contact info06@sasemas.org
Program Committee
James Bailey (University of Melbourne - Australia)
Ramesh Bharadwaj (Naval Research Lab - USA)
Steve Chien (JPL - USA)
Subrata Das (Charles River Analytics - USA)
Michael Fisher (University of Liverpool - UK)
Paolo Giorgini (University of Trento - Italy)
Mike Hinchey (Loyola College and NASA - USA)
Dieter Hutter (DFKI - Germany)
Jan Jurjens (TUM - Germany)
Tom Karygiannis (NIST - USA)
Igor Kotenko (SPIIRAS - Russia)
Wenke Lee ( Georgia Tech - USA)
Vic Lesser (University of Massachussets - USA)
Antonio Mana (University of Malaga - Spain)
Gordon Manson (University of Sheffield - UK)
Fabio Martinelli (CNR/IIT - IT)
Eduardo Fernandez Medina Paton (Universidad de Castilla - La Mancha-Spain)
Sylvan Pinsky (NSA - USA)
Stefan Poslad (Queen Mary University of London - UK)
Anita Raja (University of North Carolina - USA)
James Rash (GSFC - USA)
Chris Rouff (SAIC - USA)
Marco Roveri (IRST - Italy)
Nora Erika Sanchez (ITESM - Mexico)
Paul Scerri (CMU - USA)
Roy Sterritt (University of Ulster - UK)
Walt Truszkowski (GSFC - USA)
Michael Weiss (University of Toronto - Canada)
Wei Zhang (Boeing - USA)