EDSMLS 2020: The AAAI-20 Workshop on Engineering Dependable and Secure Machine Learning Systems Hilton New York Midtown New York City, NY, United States, February 7-8, 2020 |
Conference website | https://sites.google.com/view/edsmls2020/home |
Submission link | https://easychair.org/conferences/?conf=edsmls2020 |
Abstract registration deadline | November 15, 2019 |
Submission deadline | November 15, 2019 |
Modern society increasingly relies on machine learning (ML) solutions. Like other systems, ML systems must meet quality requirements. Standard notions of software quality and reliability such as deterministic functional correctness, black box testing, code coverage or traditional software debugging become practically irrelevant for ML systems. This is due to the nondeterministic nature of ML systems, reuse of high quality implementations of ML algorithms, and lack of understanding of the semantics of learned models, e.g., when deep learning methods are applied.
For example, self-driving car models may have been learned in a cold weather country. When such a car is deployed in a hot weather country, it will likely face dramatically different driving conditions that may render its models obsolete. This calls for novel methods and new methodologies and tools to address quality and reliability challenges of ML systems.
In addition, broad deployment of ML software in networked systems inevitably exposes the ML software to attacks. While classical security vulnerabilities are relevant, ML techniques have additional weaknesses, some already known (for example, sensitivity to training data manipulation), and some yet to be discovered. Hence, there is a need for research as well as practical solutions to ML security problems.
The workshop combines several disciplines, including ML, software engineering (with emphasis on quality), security, and algorithmic game theory. It further combines academia and industry in a quest for well-founded practical solutions.
Submission Guidelines
We solicit original papers in two formats - full (8 pages) and short (4 pages, work in progress), in AAAI format. Papers submitted to the main conference may be submitted to EDSMLS20 as well. There is no conflict here as the workshop does not have an archival publication. Rather, authors of papers accepted at both the main conference and the workshop are very welcome to participate and present at the workshop (in addition to their presentation at the main conference).
Submission is via EasyChair at the EDSMLS20 page. The reviewing process is blind. All authors of accepted papers will be invited to participate. The workshop will include paper presentation sessions. Full papers are allocated 20m presentation and 10m discussion. Short papers 10m presentation + 5m discussion.
A selection of papers from the workshop will be invited to submit a revised version to a journal special issue.
List of Topics
Topics of interest include, but are not limited, to the following:
- Software engineering aspects of ML systems and quality implications
- Testing and debugging of ML systems
- Quality implication of ML algorithms on large-scale software systems
- Case studies of successful and unsuccessful applications of ML techniques
- Correctness of data abstraction, data trust
- ML techniques to meet security and quality
- Size of the training data, implied guaranties
- Application of classical statistics to ML systems quality
- Sensitivity to data distribution diversity and distribution drift
- The effect of labeling costs on solution quality (semi-supervised learning)
- Reliable transfer learning
- Vulnerability, sensitivity and attacks against ML
- Adversarial ML and adversary based learning models
- Strategy-proof ML algorithms
Organizing committee
- Eitan Farchi (farchi@il.ibm.com), DE, Software Testing Analysis and Reviews, IBM Research, Haifa
- Onn Shehory (onn.shehory@biu.ac.il), Intelligent Information Systems, Graduate School of Business Administration, Bar Ilan University
- Guy Barash (Guy.Barash@wdc.com), Machine learning and Algorithm dev. , Western Digital Corporation, Israel
Venue
The conference will be held in Hilton New York Midtown, NYC, NY, USA