skip to main content

Explore Research Products in the NSF-PAR

Title: Global optimization of objective functions represented by ReLU networks
Neural networks can learn complex, non-convex functions, and it is challenging to guarantee their correct behavior in safety-critical contexts. Many approaches exist to find failures in networks (e.g., adversarial examples), but these cannot guarantee the absence of failures. Verification algorithms address this need and provide formal guarantees about a neural network by answering "yes or no" questions. For example, they can answer whether a violation exists within certain bounds. However, individual "yes or no" questions cannot answer qualitative questions such as “what is the largest error within these bounds”; the answers to these lie in the domain of optimization. Therefore, we propose strategies to extend existing verifiers to perform optimization and find: (i) the most extreme failure in a given input region and (ii) the minimum input perturbation required to cause a failure. A naive approach using a bisection search with an off-the-shelf verifier results in many expensive and overlapping calls to the verifier. Instead, we propose an approach that tightly integrates the optimization process into the verification procedure, achieving better runtime performance than the naive approach. We evaluate our approach implemented as an extension of Marabou, a state-of-the-art neural network verifier, and compare its performance with the bisection approach and MIPVerify, an optimization-based verifier. We observe complementary performance between our extension of Marabou and MIPVerify  more » « less
Award ID(s):
1814369
NSF-PAR ID:
10319043
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
Machine Learning
ISSN:
0885-6125
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ( , Proceedings of the 22nd International Conference on Formal Methods In Computer-Aided Design (FMCAD))
    Griggio, Alberto ; Rungta, Neha (Ed.)
    Deep neural networks (DNNs) are increasingly being employed in safety-critical systems, and there is an urgent need to guarantee their correctness. Consequently, the verification community has devised multiple techniques and tools for verifying DNNs. When DNN verifiers discover an input that triggers an error, that is easy to confirm; but when they report that no error exists, there is no way to ensure that the verification tool itself is not flawed. As multiple errors have already been observed in DNN verification tools, this calls the applicability of DNN verification into question. In this work, we present a novel mechanism for enhancing Simplex-based DNN verifiers with proof production capabilities: the generation of an easy-to-check witness of unsatisfiability, which attests to the absence of errors. Our proof production is based on an efficient adaptation of the well-known Farkas' lemma, combined with mechanisms for handling piecewise-linear functions and numerical precision errors. As a proof of concept, we implemented our technique on top of the Marabou DNN verifier. Our evaluation on a safety-critical system for airborne collision avoidance shows that proof production succeeds in almost all cases and requires only minimal overhead. 
    more » « less
  2. ; ; ; ( , Proceedings of the 27th International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS '21))
    Groote, Jan Friso ; Larsen, Kim Guldstrand (Ed.)
    Deep 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. 
    more » « less
  3. ; ; ; ; ; ; ; ; ; ; et al ( , Lecture notes in computer science)
    Deep neural networks are revolutionizing the way complex systems are designed. Consequently, there is a pressing need for tools and techniques for network analysis and certification. To help in addressing that need, we present Marabou, a framework for verifying deep neural networks. Marabou is an SMT-based tool that can answer queries about a network’s properties by transforming these queries into constraint satisfaction problems. It can accommodate networks with different activation functions and topologies, and it performs high-level reasoning on the network that can curtail the search space and improve performance. It also supports parallel execution to further enhance scalability. Marabou accepts multiple input formats, including protocol buffer files generated by the popular TensorFlow framework for neural networks. We describe the system architecture and main components, evaluate the technique and discuss ongoing work. 
    more » « less
  4. ; ; ; ( , 2023 IEEE/ACM 11th International Conference on Formal Methods in Software Engineering (FormaliSE))
    Deep Neural Networks (DNNs) have become a popular instrument for solving various real-world problems. DNNs’ sophisticated structure allows them to learn complex representations and features. For this reason, Binary Neural Networks (BNNs) are widely used on edge devices, such as microcomputers. However, architecture specifics and floating-point number usage result in an increased computational operations complexity. Like other DNNs, BNNs are vulnerable to adversarial attacks; even a small perturbation to the input set may lead to an errant output. Unfortunately, only a few approaches have been proposed for verifying BNNs.This paper proposes an approach to verify BNNs on continuous input space using star reachability analysis. Our approach can compute both exact and overapproximate reachable sets of BNNs with Sign activation functions and use them for verification. The proposed approach is also efficient in constructing a complete set of counterexamples in case a network is unsafe. We implemented our approach in NNV, a neural network verification tool for DNNs and learning-enabled Cyber-Physical Systems. The experimental results show that our star-based approach is less conservative, more efficient, and scalable than the recent SMT-based method implemented in Marabou. We also provide a comparison with a quantization-based tool EEVBNN. 
    more » « less
  5. ; ; ( , Proceedings of the ACM SIGCOMM 2022 Conference)
    Network verification often requires analyzing properties across different spaces (header space, failure space, or their product) under different failure models (deterministic and/or probabilistic). Existing verifiers efficiently cover the header or failure space, but not both, and efficiently reason about deterministic or probabilistic failures, but not both. Consequently, no single verifier can support all analyses that require different space coverage and failure models. This paper introduces Symbolic Router Execution (SRE), a general and scalable verification engine that supports various analyses. SRE symbolically executes the network model to discover what we call packet failure equivalence classes (PFECs), each of which characterises a unique forwarding behavior across the product space of headers and failures. SRE enables various optimizations during the symbolic execution, while remaining agnostic of the failure model, so it scales to the product space in a general way. By using BDDs to encode symbolic headers and failures, various analyses reduce to graph algorithms (e.g., shortest-path) on the BDDs. Our evaluation using real and synthetic topologies show SRE achieves better or comparable performance when checking reachability, mining specifications, etc. compared to state-of-the-art methods. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email