Formal Security Analysis of Neural Networks using Symbolic Intervals

04/28/2018
by   Shiqi Wang, et al.
0

Due to the increasing deployment of Deep Neural Networks (DNNs) in real-world security-critical domains including autonomous vehicles and collision avoidance systems, formally checking security properties of DNNs, especially under different attacker capabilities, is becoming crucial. Most existing security testing techniques for DNNs try to find adversarial examples without providing any formal security guarantees about the non-existence of adversarial examples. Recently, several projects have used different types of Satisfiability Modulo Theory (SMT) solvers to formally check security properties of DNNs. However, all of these approaches are limited by the high overhead caused by the solver. In this paper, we present a new direction for formally checking security properties of DNNs without using SMT solvers. Instead, we leverage interval arithmetic to formally check security properties by computing rigorous bounds on the DNN outputs. Our approach, unlike existing solver-based approaches, is easily parallelizable. We further present symbolic interval analysis along with several other optimizations to minimize overestimations. We design, implement, and evaluate our approach as part of ReluVal, a system for formally checking security properties of Relu-based DNNs. Our extensive empirical results show that ReluVal outperforms Reluplex, a state-of-the-art solver-based system, by 200 times on average for the same security properties. ReluVal is able to prove a security property within 4 hours on a single 8-core machine without GPUs, while Reluplex deemed inconclusive due to timeout (more than 5 days). Our experiments demonstrate that symbolic interval analysis is a promising new direction towards rigorously analyzing different security properties of DNNs.

READ FULL TEXT
research
01/09/2021

SyReNN: A Tool for Analyzing Deep Neural Networks

Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety ...
research
02/26/2019

Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verification

Deep neural networks (DNNs) have been shown lack of robustness for the v...
research
06/10/2021

Verifying Quantized Neural Networks using SMT-Based Model Checking

Artificial Neural Networks (ANNs) are being deployed for an increasing n...
research
01/26/2023

Learning Modulo Theories

Recent techniques that integrate solver layers into Deep Neural Networks...
research
09/19/2018

Efficient Formal Safety Analysis of Neural Networks

Neural networks are increasingly deployed in real-world safety-critical ...
research
12/21/2020

Incremental Verification of Fixed-Point Implementations of Neural Networks

Implementations of artificial neural networks (ANNs) might lead to failu...
research
03/22/2022

On Neural Network Equivalence Checking using SMT Solvers

Two pretrained neural networks are deemed equivalent if they yield simil...

Please sign up or login with your details

Forgot password? Click here to reset