SPLASH 2023
Sun 22 - Fri 27 October 2023 Cascais, Portugal
Wed 25 Oct 2023 14:36 - 14:54 at Room I - SE4AI Chair(s): Arjun Guha

We introduce a novel notion of perception contracts to reason about the safety of controllers that interact with an environment using neural perception. Perception contracts capture errors in ground-truth estimations that preserve invariants when systems act upon them. We develop a theory of perception contracts and design symbolic learning algorithms for synthesizing them from a finite set of images. We implement our algorithms and evaluate synthesized perception contracts for two realistic vision-based control systems, a lane tracking system for an electric vehicle and an agricultural robot that follows crop rows. Our evaluation shows that our approach is effective in synthesizing perception contracts and generalizes well when evaluated over test images obtained during runtime monitoring of the systems.

Wed 25 Oct

Displayed time zone: Lisbon change

14:00 - 15:30
SE4AIOOPSLA at Room I
Chair(s): Arjun Guha Northeastern University; Roblox
14:00
18m
Talk
Run-Time Prevention of Software Integration Failures of Machine Learning APIs
OOPSLA
Chengcheng Wan East China Normal University, Yuhan Liu University of Chicago, Kuntai Du University of Chicago, Henry Hoffmann University of Chicago, Junchen Jiang University of Chicago, Michael Maire University of Chicago, Shan Lu Microsoft; University of Chicago
DOI
14:18
18m
Talk
Compiling Structured Tensor Algebra
OOPSLA
Mahdi Ghorbani University of Edinburgh, Mathieu Huot University of Oxford, Shideh Hashemian University of Edinburgh, Amir Shaikhha University of Edinburgh
DOI
14:36
18m
Talk
Perception Contracts for Safety of ML-Enabled Systems
OOPSLA
Angello Astorga University of Illinois at Urbana-Champaign, Chiao Hsieh Kyoto University, P. Madhusudan University of Illinois at Urbana-Champaign, Sayan Mitra University of Illinois at Urbana-Champaign
DOI
14:54
18m
Talk
Languages with Decidable Learning: A Meta-theoremDistinguished Paper
OOPSLA
Paul Krogmeier University of Illinois at Urbana-Champaign, P. Madhusudan University of Illinois at Urbana-Champaign
DOI
15:12
18m
Talk
Deep Learning Robustness Verification for Few-Pixel Attacks
OOPSLA
Yuval Shapira Technion, Eran Avneri Technion, Dana Drachsler Cohen Technion
DOI