PROGRAM.
July 18, 2021
All times are in Pacific Time (PT)
8:30-8:50: Gathering
8:50-9:00
Opening remarks
9:00-10:00: Invited talk
An Abstract Interpretation Recipe for Machine Learning Fairness
Caterina Urban (INRIA)
Session chair: Nina Narodytska
​​
10:00-10:15: Break
10:15-11:45: Paper Session 1
Session chair: Nina Narodytska
-
10:15-10:45: Provable Repair of Deep Neural Networks
Authors: Aditya Thakur
-
10:45-11:15: An SMT-Based Approach for Verifying Binarized Neural Networks
Authors: Guy Amir, Haoze Wu, Clark Barrett and Guy Katz
-
11:15-11:45: PEREGRiNN: Penalized-Relaxation Greedy Neural Network Verifier
Authors: Haitham Khedr, James Ferlez and Yasser Shoukry
11:45-12:15: Break
12:15-1:45: Paper Session 2
Session chair: Aws Albarghouthi
-
12:15-12:45: NEUROSPF: A tool for the Symbolic Analysis of Neural Networks
Authors: Muhammad Usman, Yannic Noller, Corina S. Pasareanu, Youcheng Sun and Divya Gopinath
-
12:45-1:15: NeVer2: A Framework for Learning and Verification of Neural Networks
Authors: Dario Guidotti, Luca Pulina and Armando Tacchella
-
1:15-1:45: Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning
Authors: Zikang Xiong and Suresh Jagannathan
1:45-1:50:
Adjourn
July 19, 2021
All times are in Pacific Time (PT)
8:30-8:50: Gathering
8:50-9:00
Opening remarks
9:00-10:30: VNN-COMP
Stanley Bak (Stony Brook), Changliu Liu (CMU) and Taylor T. Johnson (Vanderbilt)
​
10:30-11:00: VNNLIB Discussion
Armando Tacchella (Genoa)
Session chair: Aws Albarghouthi
​
​
​​
11:00-11:30: Break
11:30-1:30: Paper Session 3
Session chair: Guy Katz
-
11:30-12:00: Tightening Robustness Verification of Convolutional Neural Networks with Fine-Grained Linear Approximation
Authors: Yiting Wu and Min Zhang
-
12:00-12:30: Certified Robustness to Programmable Transformations in LSTMs
Authors: Yuhao Zhang, Aws Albarghouthi and Loris D’antoni
-
12:30-1:00: Logically Constrained Pruning Towards Robust Neural Networks
Authors: Kirsty Duncan, Robert Stewart and Ekaterina Komendantskaya
-
1:00-1:30: Refutation-based Adversarial Robustness Verification of Deep Neural Networks
Authors: Joshua Smith, Jarom Allen, Viswanathan Swaminathan and Zhen Zhang
1:30-1:40:
Adjourn