Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation
Speaker:Dana Drachsler Cohen
coming from:ETH Zurich
Speakers Bio:Dana Drachsler Cohen is a postdoc in the Secure, Reliable, and Intelligent Systems Lab at the Computer Science Department at ETH Zurich. Her research interests span program synthesis, machine learning, security, and computer networks.
Event Type:SWS Colloquium
Visibility:D1, D2, D3, INET, D4, D5, SWS, RG1, MMCI
We use this to send out email in the morning.
Level:AG Audience
Language:English
Date, Time and Location
Date:Monday, 15 October 2018
Time:10:30
Duration:60 Minutes
Location:Kaiserslautern
Building:G26
Room:111
Abstract
In this talk, I will present AI2, a sound and scalable analyzer for deep neural networks. Based on overapproximation, AI2 can automatically prove safety properties (e.g., robustness) of realistic neural networks (e.g., convolutional neural networks). The key insight behind AI2 is to phrase reasoning about safety and robustness of neural networks in terms of classic abstract interpretation, enabling to leverage decades of advances in that area. To this end, I will introduce abstract transformers that capture the behavior of fully connected and convolutional neural network layers with rectified linear unit activations (ReLU), as well as max pooling layers. This allows to handle real-world neural networks, which are often built out of these types of layers. I will also empirically demonstrate that (i) AI2 is precise enough to prove useful specifications (e.g., robustness), (ii) AI2 can be used to certify the effectiveness of state-of-the-art defenses for neural networks, and (iii) AI2 is significantly faster than existing analyzers based on symbolic analysis, which often take hours to verify simple fully connected networks.
Contact
Name(s):Susanne Girard
Video Broadcast
Video Broadcast:YesTo Location:Saarbr├╝cken
To Building:E1 5To Room:029
Meeting ID:
Tags, Category, Keywords and additional notes
Note:
Attachments, File(s):
Created:
Susanne Girard/MPI-SWS, 10/10/2018 03:48 PM
Last modified:
Uwe Brahm/MPII/DE, 10/15/2018 07:01 AM
  • Susanne Girard, 10/10/2018 03:50 PM -- Created document.