Scalable Polyhedral Verification of Recurrent Neural Networks

1 code implementation • 27 May 2020 • Wonryong Ryou, Jiayu Chen, Mislav Balunovic, Gagandeep Singh, Andrei Dan, Martin Vechev

We present a scalable and precise verifier for recurrent neural networks, called Prover based on two novel ideas: (i) a method to compute a set of polyhedral abstractions for the non-convex and nonlinear recurrent update functions by combining sampling, optimization, and Fermat's theorem, and (ii) a gradient descent based algorithm for abstraction refinement guided by the certification problem that combines multiple abstractions for each neuron.

Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models

no code implementations • 19 May 2020 • Martin Kotuliak, Sandro E. Schoenborn, Andrei Dan

Our key idea is to generate adversarial objects that are unrelated to the classes identified by the target object detector.

Object object-detection +1

Securify: Practical Security Analysis of Smart Contracts

3 code implementations • 4 Jun 2018 • Petar Tsankov, Andrei Dan, Dana Drachsler Cohen, Arthur Gervais, Florian Buenzli, Martin Vechev

To address this problem, we present Securify, a security analyzer for Ethereum smart contracts that is scalable, fully automated, and able to prove contract behaviors as safe/unsafe with respect to a given property.

Cryptography and Security