Static analysis of finite precision computations
E Goubault, S Putot - … Workshop on Verification, Model Checking, and …, 2011 - Springer
We define several abstract semantics for the static analysis of finite precision computations,
that bound not only the ranges of values taken by numerical variables of a program, but also …
that bound not only the ranges of values taken by numerical variables of a program, but also …
Robustness analysis of finite precision implementations
E Goubault, S Putot - Asian Symposium on Programming Languages and …, 2013 - Springer
A desirable property of control systems is robustness to inputs, when small perturbations of
the inputs of a system will cause only small perturbations on outputs. This property should …
the inputs of a system will cause only small perturbations on outputs. This property should …
A logical product approach to zonotope intersection
We define and study a new abstract domain which is a fine-grained combination of
zonotopes with (sub-) polyhedric domains such as the interval, octagon, linear template or …
zonotopes with (sub-) polyhedric domains such as the interval, octagon, linear template or …
Robustness verification of support vector machines
We study the problem of formally verifying the robustness to adversarial examples of support
vector machines (SVMs), a major machine learning model for classification and regression …
vector machines (SVMs), a major machine learning model for classification and regression …
Utilizing dependencies to obtain subsets of reachable sets
N Kochdumper, B Schürmann, M Althoff - Proceedings of the 23rd …, 2020 - dl.acm.org
Reachability analysis, in general, is a fundamental method that supports formally-correct
synthesis, robust model predictive control, set-based observers, fault detection, invariant …
synthesis, robust model predictive control, set-based observers, fault detection, invariant …
Inner approximated reachability analysis
Computing a tight inner approximation of the range of a function over some set is notoriously
difficult, way beyond obtaining outer approximations. We propose here a new method to …
difficult, way beyond obtaining outer approximations. We propose here a new method to …
A generalization of p-boxes to affine arithmetic
We often need to deal with information that contains both interval and probabilistic
uncertainties. P-boxes and Dempster–Shafer structures are models that unify both kind of …
uncertainties. P-boxes and Dempster–Shafer structures are models that unify both kind of …
Extensions of polynomial zonotopes and their application to verification of cyber-physical systems
N Kochdumper - 2022 - mediatum.ub.tum.de
In this thesis, we present the three novel set representations sparse polynomial zonotopes,
constrained polynomial zonotopes, and the Z-representation of polytopes. One major …
constrained polynomial zonotopes, and the Z-representation of polytopes. One major …
[HTML][HTML] Shared certificates for neural network verification
Existing neural network verifiers compute a proof that each input is handled correctly under
a given perturbation by propagating a symbolic abstraction of reachable values at each …
a given perturbation by propagating a symbolic abstraction of reachable values at each …
Robustness certification of k-nearest neighbors
N Fassina, F Ranzato, M Zanella - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
We study the certification of stability properties, such as robustness and individual fairness,
of the k-Nearest Neighbor algorithm (kNN). Our approach leverages abstract interpretation …
of the k-Nearest Neighbor algorithm (kNN). Our approach leverages abstract interpretation …