Dario Guidotti

Dario Guidotti, Luca Pulina, Armando Tacchella

In this work, we present an early prototype of NeVer 2.0, a new system for automated synthesis and analysis of deep neural networks.NeVer 2.0borrows its design philosophy from NeVer, the first package that integrated learning, automated verification and repair of (shallow) neural networks in a single tool. The goal of NeVer 2.0 is to provide a similar integration for deep networks by leveraging a selection of state-of-the-art learning frameworks and integrating them with verification algorithms to ease the scalability challenge and make repair of faulty networks possible.

Dario Guidotti, Francesco Leofante, Luca Pulina et al.

Verification of deep neural networks has witnessed a recent surge of interest, fueled by success stories in diverse domains and by abreast concerns about safety and security in envisaged applications. Complexity and sheer size of such networks are challenging for automated formal verification techniques which, on the other hand, could ease the adoption of deep networks in safety- and security-critical contexts. In this paper we focus on enabling state-of-the-art verification tools to deal with neural networks of some practical interest. We propose a new training pipeline based on network pruning with the goal of striking a balance between maintaining accuracy and robustness while making the resulting networks amenable to formal analysis. The results of our experiments with a portfolio of pruning algorithms and verification tools show that our approach is successful for the kind of networks we consider and for some combinations of pruning and verification techniques, thus bringing deep neural networks closer to the reach of formally-grounded methods.