Tue 25 Jun 2019 15:00 - 15:20 at 224AB - Reasoning and Optimizing ML Models Chair(s): Martin Maas

In recent years, the notion of local robustness (or robustness for short) has emerged as a desirable property of deep neural networks. Intuitively, robustness means that small perturbations to an input do not cause the network to perform misclassifications. In this paper, we present a novel algorithm for verifying robustness properties of neural networks. Our method synergistically combines gradient-based optimization methods for counterexample search with abstraction-based proof search to obtain a sound and (δ -)complete decision procedure. Our method also employs a data-driven approach to learn a verification policy that guides abstract interpretation during proof search. We have implemented the proposed approach in a tool called Charon and experimentally evaluated it on hundreds of benchmarks. Our experiments show that the proposed approach significantly outperforms three state-of-the-art tools, namely AI^2, Reluplex, and Reluval.

Tue 25 Jun

Displayed time zone: Tijuana, Baja California change

14:00 - 15:30
Reasoning and Optimizing ML ModelsPLDI Research Papers at 224AB
Chair(s): Martin Maas Google
14:00
20m
Talk
An Inductive Synthesis Framework for Verifiable Reinforcement Learning
PLDI Research Papers
He Zhu Rutgers University, USA, Zikang Xiong Purdue University, Stephen Magill , Suresh Jagannathan Purdue University
Media Attached
14:20
20m
Talk
Programming Support for Autonomizing Software
PLDI Research Papers
Wen-Chuan Lee Purdue University, Peng Liu Purdue University, Yingqi Liu Purdue University, USA, Shiqing Ma Purdue University, USA, Xiangyu Zhang Purdue University
14:40
20m
Talk
Wootz: A Compiler-Based Framework for Fast CNN Pruning via Composability
PLDI Research Papers
Hui Guan North Carolina State University, Xipeng Shen North Carolina State University, Seung-Hwan Lim Oak Ridge National Laboratory, USA
Media Attached File Attached
15:00
20m
Talk
Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness
PLDI Research Papers
Greg Anderson University of Texas at Austin, USA, Shankara Pailoor University of Texas at Austin, USA, Isil Dillig UT Austin, Swarat Chaudhuri Rice University
Media Attached