scholarly journals Simplifying Neural Networks Using Formal Verification

2020 ◽  
pp. 85-93 ◽  
Author(s):  
Sumathi Gokulanathan ◽  
Alexander Feldsher ◽  
Adi Malca ◽  
Clark Barrett ◽  
Guy Katz
Keyword(s):  
Neural Networks ◽  
Formal Verification

scholarly journals Formal verification of neural agents in non-deterministic environments

2021 ◽  
Vol 36 (1) ◽  
Author(s):  
Michael E. Akintunde ◽  
Elena Botoeva ◽  
Panagiotis Kouvaros ◽  
Alessio Lomuscio
Keyword(s):  
Neural Networks ◽  
Parallel Algorithms ◽  
Formal Verification ◽  
Experimental Results ◽  
Use Case ◽  
Feed Forward ◽  
Verification Problem ◽  
Bounded Fragment

AbstractWe introduce a model for agent-environment systems where the agents are implemented via feed-forward ReLU neural networks and the environment is non-deterministic. We study the verification problem of such systems against CTL properties. We show that verifying these systems against reachability properties is undecidable. We introduce a bounded fragment of CTL, show its usefulness in identifying shallow bugs in the system, and prove that the verification problem against specifications in bounded CTL is in coNExpTime and PSpace-hard. We introduce sequential and parallel algorithms for MILP-based verification of agent-environment systems, present an implementation, and report the experimental results obtained against a variant of the VerticalCAS use-case and the frozen lake scenario.

scholarly journals How Many Bits Does it Take to Quantize Your Neural Network?

2020 ◽  
pp. 79-97 ◽  
Author(s):  
Mirco Giacobbe ◽  
Thomas A. Henzinger ◽  
Mathias Lechner
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fixed Point ◽  
Formal Verification ◽  
Real Time ◽  
Gender Bias ◽  
Embedded Devices ◽  
Standard Practice ◽  
Verification Method ◽  
Smt Solving

Abstract Quantization converts neural networks into low-bit fixed-point computations which can be carried out by efficient integer-only hardware, and is standard practice for the deployment of neural networks on real-time embedded devices. However, like their real-numbered counterpart, quantized networks are not immune to malicious misclassification caused by adversarial attacks. We investigate how quantization affects a network’s robustness to adversarial attacks, which is a formal verification question. We show that neither robustness nor non-robustness are monotonic with changing the number of bits for the representation and, also, neither are preserved by quantization from a real-numbered network. For this reason, we introduce a verification method for quantized neural networks which, using SMT solving over bit-vectors, accounts for their exact, bit-precise semantics. We built a tool and analyzed the effect of quantization on a classifier for the MNIST dataset. We demonstrate that, compared to our method, existing methods for the analysis of real-numbered networks often derive false conclusions about their quantizations, both when determining robustness and when detecting attacks, and that existing methods for quantized networks often miss attacks. Furthermore, we applied our method beyond robustness, showing how the number of bits in quantization enlarges the gender bias of a predictor for students’ grades.

Formal verification of wastewater treatment processes using events detected from continuous signals by means of artificial neural networks. Case study: SBR plant

2010 ◽  
Vol 25 (5) ◽  
pp. 648-660 ◽  
Author(s):  
Luca Luccarini ◽  
Gianni Luigi Bragadin ◽  
Gabriele Colombini ◽  
Maurizio Mancini ◽  
Paola Mello ◽  
...  
Keyword(s):  
Neural Networks ◽  
Wastewater Treatment ◽  
Artificial Neural Networks ◽  
Formal Verification ◽  
Treatment Processes ◽  
Artificial Neural

scholarly journals An SMT-Based Approach for Verifying Binarized Neural Networks

2021 ◽  
pp. 203-222
Author(s):  
Guy Amir ◽  
Haoze Wu ◽  
Clark Barrett ◽  
Guy Katz
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Formal Verification ◽  
Software Systems ◽  
Network Architectures ◽  
Security Issues ◽  
The Neural Network ◽  
Network Verification ◽  
Promising Avenue

AbstractDeep learning has emerged as an effective approach for creating modern software systems, with neural networks often surpassing hand-crafted systems. Unfortunately, neural networks are known to suffer from various safety and security issues. Formal verification is a promising avenue for tackling this difficulty, by formally certifying that networks are correct. We propose an SMT-based technique for verifying binarized neural networks — a popular kind of neural network, where some weights have been binarized in order to render the neural network more memory and energy efficient, and quicker to evaluate. One novelty of our technique is that it allows the verification of neural networks that include both binarized and non-binarized components. Neural network verification is computationally very difficult, and so we propose here various optimizations, integrated into our SMT procedure as deduction steps, as well as an approach for parallelizing verification queries. We implement our technique as an extension to the Marabou framework, and use it to evaluate the approach on popular binarized neural network architectures.

Determination of S-N curves with the application of artificial neural networks

1999 ◽  
Vol 22 (8) ◽  
pp. 723-728 ◽  
Author(s):  
Artymiak ◽  
Bukowski ◽  
Feliks ◽  
Narberhaus ◽  
Zenner
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document