activity
20152023
most citedTowards Proving the Adversarial Robustness of Deep Neural Networks

119 citations · 465 across the 38 of their papers we have counts for

collaborators
Showing 2018Show all

5 papers · 1 filter

cs.CR2018

Processor Hardware Security Vulnerabilities and their Detection by Unique Program Execution Checking

Mohammad Rahmani Fadiheh, Dominik Stoffel, Clark Barrett +2

Recent discovery of security attacks in advanced processors, known as Spectre and Meltdown, has resulted in high public alertness about security of hardware. The root cause of thes…

cs.LO2018★ 3 cited

CVC4 at the SMT Competition 2018

Clark Barrett, Haniel Barbosa, Martin Brain +8

This paper is a description of the CVC4 SMT solver as entered into the 2018 SMT Competition. We only list important differences from the 2017 SMT Competition version of CVC4. For f…

cs.LO2018

On Solving Quantified Bit-Vectors using Invertibility Conditions

Aina Niemetz, Mathias Preiner, Andrew Reynolds +2

We present a novel approach for solving quantified bit-vector formulas in Satisfiability Modulo Theories (SMT) based on computing symbolic inverses of bit-vector operators. We deri…

cs.AI2018★ 19 cited

Toward Scalable Verification for Safety-Critical Deep Networks

Lindsey Kuper, Guy Katz, Justin Gottschlich +3

The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability. Form…

cs.LO2018

EMME: a formal tool for ECMAScript Memory Model Evaluation

Cristian Mattarei, Clark Barrett, Shu-yu Guo +3

Nearly all web-based interfaces are written in JavaScript. Given its prevalence, the support for high performance JavaScript code is crucial. The ECMA Technical Committee 39 (TC39)…