SAIV 2024

Program

# Main Room
9:00

Verified Autonomy with Neural Lyapunov Barrier Certificates

Clark Barrett

Keynote Chair: Mirco Giacobbe 

:30
10:00

Chronosymbolic Learning: Efficient CHC Solving with Symbolic Reasoning and Inductive Learning

Ziyan Luo, Xujie Si

Paper Chair: Mirco Giacobbe 

:30

Coffee break

11:00

Provable Preimage Under-Approximation for Neural Networks

Xiyue Zhang, Benjie Wang, Marta Kwiatkowska

Chair: Ravi Mangal 

:30

Provably Safe Neural Network Controllers via Differential Dynamic Logic

Samuel Teuber, Stefan Mitsch, André Platzer

Chair: Ravi Mangal 

12:00

Error Analysis of Shapley Value-Based Model Explanations: An Informative Perspective

Ningsheng Zhao, Jia Yuan Yu, Krzysztof Dzieciolowski, Trang Bui

Paper Chair: Ravi Mangal 

:30

Lunch

13:00
:30
14:00

Verification of Neuro-Symbolic Multi-Agent Systems

Elena Botoeva

Table Host Chair: Guy Katz 

:30

Towards Probabilistic Verification of AI Systems via Weighted Model Integration

Paolo Morettin

Table Host Chair: Guy Katz 

15:00

Round-table discussion

:30

Coffee break

16:00

Marabou 2.0: A Versatile Formal Analyzer of Neural Networks

Haoze Wu, Omri Isac, Aleksandar Zeljić, Teruhiro Tagomori, Matthew Daggitt, Wen Kokke, Idan Refaeli, Guy Amir, Kyle Julian, Shahaf Bassan, Pei Huang, Ori Lahav, Min Wu, Min Zhang, Ekaterina Komendantskaya, Guy Katz, Clark Barrett

Chair: Christopher Brix 

:30

Concept-based Analysis of Neural Networks via Vision-Language Models

Ravi Mangal, Nina Narodytska, Divya Gopinath, Boyue Caroline Hu, Anirban Roy, Susmit Jha, Corina Păsăreanu

Paper Chair: Christopher Brix 

17:00

Parallel Verification for δ-Equivalence of Neural Network Quantization

Pei Huang, Yuting Yang, Haoze Wu, Ieva Daukantas, Min Wu, Fuqi Jia, Clark Barrett

Paper Chair: Christopher Brix 

:30

Verification of Neural Network Control Systems in Continuous Time

Ali ArjomandBigdeli, Andrew Mata, Stanley Bak

Paper Chair: Christopher Brix 

# Main Room
9:00

Machine Learning Meets Program Reasoning: Opportunities and Challenges

Xujie Si

Table Host Chair: Taylor Johnson 

:30

Trustworthy-by-Design Autonomous AI Systems

Shufang Zhu

Table Host Chair: Taylor Johnson 

10:00

Round-table discussion

:30

Coffee break

11:00

Boosting Few-Pixel Robustness Verification via Covering Verification Designs

Yuval Shapira, Naor Wiesel, Shahar Shabelman, Dana Drachsler-Cohen

Chair: Andoni Rodriguez 

:30

A Preliminary Study to Examining Per-Class Performance Bias via Robustness Distributions

Annelot Bosman, Anna Münz, Holger Hoos, Jan van Rijn

Paper Chair: Andoni Rodriguez 

12:00

Iterative Counter-Example Guided Robustness Verification for Neural Networks

Karthik Hanumanthaiah, Samik Basu

Abstract Chair: Andoni Rodriguez 

:30

Lunch

13:00
:30
14:00

VNN-COMP

Taylor T. Johnson

Chair: Ekaterina Komendantskaya 

:30
15:00

Clover: Closed-Loop Verifiable Code Generation

Chuyue Sun, Ying Sheng, Oded Padon, Clark Barrett

Paper Chair: Ekaterina Komendantskaya 

:30

Coffee break

16:00

Provable Repair of Vision Transformers

Stephanie Nawas, Zhe Tao, Aditya Thakur

Paper Chair: Yuval Shapira 

:30

Scalable relational verification and training for deep neural networks

Debangshu Banerjee, Changming Xu, Gagandeep Singh

Chair: Yuval Shapira 

17:00

Shield Synthesis Modulo Theories

Andoni Rodriguez, Guy Amir, Davide Corsi, César Sánchez, Guy Katz

Chair: Yuval Shapira 

:30

Generating Explanations for Decisions of Classifiers using Instance Abstractions

Chunxi Ji, Adnan Darwiche

Chair: Yuval Shapira 

Caption
Invited Talk
Presentation
VNN-COMP
Discussion
Break