FoMLAS: 2nd CfP (ETAPS'18 workshop)

by Chih-Hong Cheng, Feb. 6, 2018

This goal of FoMLAS workshop is to initiate discussion regarding how formal methods can be used to increase predictability, explainability, and accountability of machine learning (ML) enabled autonomous systems.


First Workshop on

Formal Methods for ML-Enabled Autonomous Systems

(FoMLAS 2018)

April 20, 2018

Affiliated With ETAPS 2018

Thessaloniki, Greece


  • Dr. Simon Burton from BOSCH on ML for safety-critical automotive
  • Dr. Mauricio Castillo-Effen from GE research on ML for safety-critical avionics
  • Dr. John Rushby from SRI International on certification
  • Dr. Xiaowei Huang from Univ. Liverpool on formal verification and testing of neural networks
  • Dr. Alhussein Fawzi from UCLA on adversarial examples in neural networks



After the well-known DARPA Urban challenge, there have been significant improvements towards autonomous driving. In the past few years, the major theme when building self-driving cars has shifted to deep learning and probabilistic techniques. When these new algorithms act as key components in autonomous driving, they create substantial technological challenges in terms of explainability (e.g., can I explain what is happening inside the machine-learning algorithm?), predictability and correctness (e.g., can I predict what will happen next in the algorithm, or how good can the machine learning component generalize?), and accountability (e.g., when an accident occurs, can one find the root cause, or who is the one to blame?).

This goal of this workshop is to facilitate discussion regarding how formal methods can be used to increase predictability, explainability, and accountability of ML-enabled autonomous systems. The workshop welcomes results from concept formulation (by connecting these concepts with existing research topics in logic and games), as well as algorithms, tools or concrete case studies.



Submissions must be unpublished and not be submitted for publication elsewhere. Full papers are limited to 12 pages EPTCS style (not counting the appendices). Short papers and extended abstracts are welcome, which are limited to 6 pages EPTCS style.

Submissions must be in English and submitted in PDF format via EasyChair (

All submissions will be peer reviewed by at least three referees. Papers will be judged based on their novelty, relevance and technical merit.



  • Submission date: 10 February 2018 
  • Notification date: 3 March 2018 
  • Final papers due: 24 March 2018
  • EPTCS proceedings due: 1 May 2018



Workshop Co-chairs

Advisory board

  • Harald Ruess, fortiss, Germany 
  • John Rushby, SRI International, USA  
Program Committee 

  • Yu-Fang Chen, Academia Sinica, Taiwan
  • Jyotirmoy Deshmukh, USC, USA 
  • Rüdiger Ehlers, Univ. Bremen, Germany
  • Susmit Jha, SRI International, USA
  • Xiaowei Huang, Univ. Liverpool, UK
  • Rupak Majumdar, MPI-SWS, Germany 
  • Ivan Papusha, UT Austin, USA 
  • Harald Ruess, fortiss, Germany 
  • John Rushby, SRI International, USA 
  • Starvos Tripakis, Aalto University, Finland

Local arrangement

  • Georg Nührenberg, fortiss - Landesforschungsinstitut des Freistaats Bayern



Chih-Hong Cheng <>

Indranil Saha <>