Maximum Resilience of Artificial Neural Networks

2017/04/28 by Chih‐Hong Cheng, Cheng, Chih-Hong, Georg Nührenberg +3 · 9 citations
Computer Science · Engineering · #Advanced Memory and Neural Computing #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Logic in Computer Science (cs.LO) #Machine Learning (cs.LG) #Software Engineering (cs.SE)

paper · pdf · doi:10.48550/arxiv.1705.01040

openalex publication_date 2017/04/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The deployment of Artificial Neural Networks (ANNs) in safety-critical applications poses a number of new verification and certification challenges. In particular, for ANN-enabled self-driving vehicles it is important to establish properties about the resilience of ANNs to noisy or even maliciously manipulated sensory input. We are addressing these challenges by defining resilience properties of ANN-based classifiers as the maximal amount of input or sensor perturbation which is still tolerated. This problem of computing maximal perturbation bounds for ANNs is then reduced to solving mixed integer optimization problems (MIP). A number of MIP encoding heuristics are developed for drastically reducing MIP-solver runtimes, and using parallelization of MIP-solvers results in an almost linear speed-up in the number (up to a certain limit) of computing cores in our experiments. We demonstrate the effectiveness and scalability of our approach by means of computing maximal resilience bounds for a number of ANN benchmark sets ranging from typical image recognition scenarios to the autonomous maneuvering of robots.

Citations

• End to End Learning for Self-Driving Cars
• Practical Black-Box Attacks against Machine Learning

Cited by

• Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
• Neural Two-Stage Stochastic Volt-VAR Optimization for Three-Phase Unbalanced Distribution Systems with Network Reconfiguration
• Towards Strong Certified Defense with Universal Asymmetric Randomization
• Efficient Neural Network Verification via Order Leading Exploration of Branch-and-Bound Trees
• Neural Two-Stage Stochastic Optimization for Solving Unit Commitment Problem
• Towards Fast Computation of Certified Robustness for ReLU Networks
• Interior-Point Vanishing Problem in Semidefinite Relaxations for Neural Network Verification
• Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees
• BenLOC: A Benchmark for Learning to Configure MIP Optimizers

Related

• Efficient Formal Safety Analysis of Neural Networks
• Neural Networks for Safety-Critical Applications - Challenges, Experiments and Perspectives
• Estimating Neural Network Robustness via Lipschitz Constant and Architecture Sensitivity
• An Estimator for the Sensitivity to Perturbations of Deep Neural Networks
• Benchmarking Neural Network Robustness to Common Corruptions and Perturbations