Isabella Mastroeni

Luca Marzari, Isabella Mastroeni, Alessandro Farinelli

Traditional methods for formal verification (FV) of deep neural networks (DNNs) are constrained by a binary encoding of safety properties, where a model is classified as either safe or unsafe (robust or not robust). This binary encoding fails to capture the nuanced safety levels within a model, often resulting in either overly restrictive or too permissive requirements. In this paper, we introduce a novel problem formulation called Abstract DNN-Verification, which verifies a hierarchical structure of unsafe outputs, providing a more granular analysis of the safety aspect for a given DNN. Crucially, by leveraging abstract interpretation and reasoning about output reachable sets, our approach enables assessing multiple safety levels during the FV process, requiring the same (in the worst case) or even potentially less computational effort than the traditional binary verification approach. Specifically, we demonstrate how this formulation allows rank adversarial inputs according to their abstract safety level violation, offering a more detailed evaluation of the model's safety and robustness. Our contributions include a theoretical exploration of the relationship between our novel abstract safety formulation and existing approaches that employ abstract interpretation for robustness verification, complexity analysis of the novel problem introduced, and an empirical evaluation considering both a complex deep reinforcement learning task (based on Habitat 3.0) and standard DNN-Verification benchmarks.

Nicola Assolini, Luca Marzari, Isabella Mastroeni et al.

Variational quantum circuits (VQCs) are a central component of many quantum machine learning algorithms, offering a hybrid quantum-classical framework that, under certain aspects, can be considered similar to classical deep neural networks. A shared aspect is, for instance, their vulnerability to adversarial inputs, small perturbations that can lead to incorrect predictions. While formal verification techniques have been extensively developed for classical models, no comparable framework exists for certifying the robustness of VQCs. Here, we present the first in-depth theoretical and practical study of the formal verification problem for VQCs. Inspired by abstract interpretation methods used in deep learning, we analyze the applicability and limitations of interval-based reachability techniques in the quantum setting. We show that quantum-specific aspects, such as state normalization, introduce inter-variable dependencies that challenge existing approaches. We investigate these issues by introducing a novel semantic framework based on abstract interpretation, where the verification problem for VQCs can be formally defined, and its complexity analyzed. Finally, we demonstrate our approach on standard verification benchmarks.

Isabella Mastroeni, Vincenzo Arceri

In this paper, our aim is to propose a model for code abstraction, based on abstract interpretation, allowing us to improve the precision of a recently proposed static analysis by abstract interpretation of dynamic languages. The problem we tackle here is that the analysis may add some spurious code to the string-to-execute abstract value and this code may need some abstract representations in order to make it analyzable. This is precisely what we propose here, where we drive the code abstraction by the analysis we have to perform.