Afternoon Poster Session
in
Workshop: 2nd Workshop on Formal Verification of Machine Learning
Abstract
"Meaning in Language Models: A Formal Semantics Approach" Charles Jin (MIT)*; Martin Rinard (MIT)
"Provably Correct Physics-Informed Neural Networks" Francisco Girbal Eiras (University of Oxford)*; Adel Bibi (University of Oxford); Rudy Bunel (Deepmind); Krishnamurthy Dvijotham (Google Research); Philip Torr (University of Oxford); M. Pawan Kumar (Google DeepMind)
"Your Value Function is a Control Barrier Function" Daniel CH Tan (University College London)*; Fernando Acero (University College London); Robert McCarthy (University College London); Dimitrios Kanoulas (University College London); Zhibin (Alex) Li (University College London)
"Constraint Satisfied Sampling for Formal Verification in Geometric Deep Learning and Molecular Modelling" Justin S Diamond (University of Basel)*; Markus Lill (University of Basel)
"One Pixel Adversarial Attacks via Sketched Programs" Tom Yuviler (Technion)*; Dana Drachsler-Cohen (Technion)
"Robustness Verification for Perception Models against Camera Motion Perturbations" Hanjiang Hu (Carnegie Mellon University)*; Changliu Liu (Carnegie Mellon University); DING ZHAO (Carnegie Mellon University)
"Efficient Estimation of Local Robustness of Machine Learning Models" Tessa Han (Harvard University)*; Suraj Srinivas (Harvard University); Himabindu Lakkaraju (Harvard)
"(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy" Elan Rosenfeld (Carnegie Mellon University)*; Saurabh Garg (CMU)
"Learning Counterfactually Invariant Predictors" Francesco Quinzan (Hasso Plattner Institute)*; Cecilia Casolo (Helmholtz München); John Doe (Dark Matter); Yucen Luo (Max Planck Institute for Intelligent Systems); Niki Kilbertus (Helmholtz AI)
"Interpreting Robustness Proofs of Deep Neural Networks" Debangshu Banerjee (University of Illinois Urbana-Champaign)*; Avaljot Singh (UIUC); Gagandeep Singh (VMware Research and UIUC)
"Connecting Certified and Adversarial Training" Yuhao Mao (ETH Zurich); Mark Niklas Müller (ETH Zurich)*; Marc Fischer (ETH Zurich); Martin Vechev (ETH Zurich)