Talks
Invited Talk
-
Table Host Chair: Anna Lukina
-
Ensuring Reliable Outcomes in Deep Learning: The Key Role of Requirements
Table Host Chair: Mirco Giacobbe
-
From ε-Balls to Semantics: Towards Verifiable NLP Pipelines
Table Host Chair: Mirco Giacobbe
-
Soft Pattern Matching: Toward Runtime Verification of NLP Systems
Table Host Chair: Mirco Giacobbe
-
(Hybrid) Perspectives: Opportunities at the intersection of FM and AI
Presentation
-
Bridging Neural ODE and ResNet: A Formal Error Bound for Safety Verification
Abdelrahman Sayed Sayed, Pierre-Jean Meyer, Mohamed Ghazel
Paper Chair: Edoardo Manino
-
Abstraction-Based Proof Production in Formal Verification of Neural Networks
Yizhak Yisrael Elboher, Omri Isac, Guy Katz, Tobias Ladner, Haoze Wu
Paper Chair: Kaushik Mallik
-
Probabilistic verification of neural networks with sampling-based Probability Box propagation
Marcel Chwiałkowski, Sylvie Putot, Eric Goubault
Paper Chair: Elena Botoeva
-
How to Verify Generalization Capability of a Neural Network with Formal Methods
Arthur Clavière, Dmitrii Kirov, Darren Cofer
Paper Chair: Taylor Johnson
-
On the Complexity of Formal Reasoning in State Space Models
Paper Chair: Taylor Johnson
-
Neural Network Verification for Gliding Drone Control: A Case Study
Colin Kessler, Ekaterina Komendantskaya, Marco Casadio, Ignazio Maria Viola, Albaraa Ammar Othman, Alistair Malhotra, Robbie McPherson
Paper Chair: Edoardo Manino
-
Scenario-based Compositional Verification of Autonomous Systems
Christopher Watson, Rajeev Alur, Divya Gopinath, Ravi Mangal, Corina S. Pasareanu
Paper Chair: Edoardo Manino
-
(Hybrid) ClassInvGen: Class Invariant Synthesis using Large Language Models
Chuyue Sun, Saikat Chakraborty, Jubi Taneja, Viraj Agashe, Xiaokang Qiu, David L. Dill, Clark Barrett, Shuvendu K Lahiri
Paper Chair: Luca Arnaboldi
-
Quantifiers for Differentiable Logics in Rocq
Jairo Miguel Marulanda-Giraldo, Ekaterina Komendantskaya, Alessandro Bruni, Reynald Affeldt, Matteo Capucci, Enrico Marchioni
Paper Chair: Luca Arnaboldi
-
(Hybrid) GRENA: GPU-aided Abstract Refinement for Neural Network Verification
Yuyi Zhong, Shaun Tan Zong Zhi, Hanping Xu, Siau-Cheng Khoo
Paper Chair: Elena Botoeva
-
Robustness Margin: A new measure for the robustness of neural networks
Lionel Kielhofer, Annelot Willemijn Bosman, Jan N. van Rijn, Holger Hoos
Paper Chair: Kaushik Mallik
-
CTRAIN - A Training Library for Certifiably Robust Neural Networks
Konstantin Kaulen, Holger Hoos
Paper Chair: Kaushik Mallik
-
Certified Error Analysis of Homomorphically Encrypted Neural Networks
Philipp Daniel Kern, Edoardo Manino, Carsten Sinz
Paper Chair: Elena Botoeva
VNN-COMP
-
Chair: Mirco Giacobbe
Discussion
-
Panel with all invited speakers
-
Round-table discussion
on Mon, 10:00 in D-152 (D-building, 1st floor)
Break
-
Lunch
on Mon, 12:00 in D-152 (D-building, 1st floor)
Posters
-
Coffee/Tea & Posters
on Mon, 10:30 in D-152 (D-building, 1st floor)
-
Analyzing Adversarial Inputs in Deep Reinforcement Learning
Davide Corsi, Guy Amir, Guy Katz, Alessandro Farinelli
Poster
-
Logic Gate Neural Networks are Good for Verification
Fabian Kresse, Emily Yu, Christoph H Lampert, Thomas A Henzinger
Poster
-
VERONA: A Framework for Neural Network Robustness Experiments
Aaron Berger, Annelot Willemijn Bosman, Holger Hoos, Jan N van Rijn
Poster
-
Monitoring Robustness and Individual Fairness
Konstantin Kueffner, Kaushik Mallik, Ashutosh Gupta, Thomas A Henzinger, David Pape
Poster
-
Automated VNN Solver Configuration Selection via Deep Reinforcement Learning
Salil Kamath, Matthew Davis, Jonathan Andreasen, Yatis Dodia, Vijay Ganesh
Poster
-
Neural Approximation of Vision-Controlled Systems for Reachability Analysis
Yuang Geng, Sukanth Sundaran, Chao Huang, Steven Drager, Ivan Ruchkin
Poster
-
Composing Reinforcement Learning Policies, with Formal Guarantees
Florent Delgrange, Guy Avni, Anna Lukina, Christian Schilling, Ann Nowe, Guillermo A. Pérez
Poster
-
Stream-Based Monitoring of Algorithmic Fairness
Frederik Scheerer, Jan Baumeister, Julian Siber, Bernd Finkbeiner
Poster
-
Comparing Differentiable Logics for Learning with Logical Constraints
Thomas Flinkow, Barak A Pearlmutter, Rosemary Monahan
Poster
-
False Positives in Robustness Checking of Neural Networks - An Experimental Study
Mohammad Afzal, S Akshay, Ashutosh Gupta, Venkatesh R
Poster
-
On the efficiency of training robust decision trees
Benedict Gerlach, Marie Anastacio, Holger Hoos
Poster
-
Formally Verifying Stock Classifiers: A Case Study
Guy Amir, Daniel Wiedenmann, Guy Katz
Poster
-
Glitches in Tree Ensemble model
Namrita Varshney, Ashutosh Gupta, Shankaranarayanan Krishna, Kaushik Mallik, Satyankar Chandra
Poster
-
Qualitative and quantitative verification of DNN-CPS models
Letian Fang, Jing Liu, Jiang Xiong, Rongbin Hou
Poster
-
Certificate-Guided Evaluation of Reinforcement Learning Generalization
Vignesh Subramanian, Đorđe Žikelić, Suguman Bansal
Poster
-
Revisiting Differential Verification: Equivalence Verification with Confidence
Samuel Teuber, Philipp Daniel Kern, Marvin Janzen, Bernhard Beckert
Poster
-
Dynamic Back-Substitution in Bound-Propagation-Based Neural Network Verification
Panagiotis Kouvaros, Benedikt Brückner, Patrick Henriksen, Alessio Lomuscio
Poster
-
Verification of Neural Networks against Convolutional Perturbations via Parameterised Kernels
Benedikt Brückner, Alessio Lomuscio
Poster
-
Dynamic Algorithm Termination for Branch-and-Bound-based Neural Network Verification
Konstantin Kaulen, Matthias König, Holger Hoos
Poster
-
Semantic Robustness Verification for Neural Networks using Image Similarity Measures
Jannick Strobel, David Boetius, Paolo Arcaini, Fuyuki Ishikawa, Stefan Leue
Poster
-
Neural Control and Certificate Repair via Runtime Monitoring
Emily Yu, Đorđe Žikelić, Thomas A Henzinger
Poster
-
Control Barrier Functions with Lookahead
Thomas A Henzinger, Kaushik Mallik, Emily Yu, Đorđe Žikelić
Poster