paper-with-me

Papers

PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks

2024-08-17 · Xiyue Zhang, Benjie Wang, Marta Kwiatkowska, huan zhang

Most methods for neural network verification focus on bounding the image, i.e., set of outputs for a given input set. This can be used to, for example, check the robustness of neural network predictions to bounded perturbations of an input. However, verifying properties concerning the preimage, i.e., the set of inputs satisfying an output property, requires abstractions in the input space. We present a general framework for preimage abstraction that produces under- and over-approximations of any polyhedral output set. Our framework employs cheap parameterised linear relaxations of the neural network, together with an anytime refinement procedure that iteratively partitions the input region by splitting on input features and neurons. The effectiveness of our approach relies on carefully designed heuristics and optimization objectives to achieve rapid improvements in the approximation volume. We evaluate our method on a range of tasks, demonstrating significant improvement in efficiency and scalability to high-input-dimensional image classification tasks compared to state-of-the-art techniques. Further, we showcase the application to quantitative verification and robustness analysis, presenting a sound and complete algorithm for the former and providing sound quantitative results for the latter.

📄 PDF Abstract BibTeX arXiv:2408.09262

Code (1)

zhang-xiyue/preimageapproxfornns 공식 구현 pytorch

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음

Similar Papers 제목 키워드 기반

Efficient Preimage Approximation for Neural Network Certification

2025-05-28 · Anton Björklund, Mykola Zaitsev, Marta Kwiatkowska

The growing reliance on artificial intelligence in safety- and security-critical applications demands effective neural network certification. A challenging real-world use case is certification against ``patch attacks'', …

Provable Preimage Under-Approximation for Neural Networks (Full Version)

2023-05-05 · Xiyue Zhang, Benjie Wang, Marta Kwiatkowska

Neural network verification mainly focuses on local robustness properties, which can be checked by bounding the image (set of outputs) of a given input set. However, often it is important to know whether a given property…

On the Probabilistic Learnability of Compact Neural Network Preimage Bounds

2025-11-10 · Luca Marzari, Manuele Bicego, Ferdinando Cicalese, Alessandro Farinelli arxiv

Although recent provable methods have been developed to compute preimage bounds for neural networks, their scalability is fundamentally limited by the #P-hardness of the problem. In this work, we adopt a novel probabilis…

PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs

2025-10-29 · Jaewon Chu, Seunghun Lee, Hyunwoo J. Kim arxiv

Large language models (LLMs) have achieved remarkable success across diverse domains, due to their strong instruction-following capabilities. This has led to increasing interest in optimizing instructions for black-box L…

The inverse problem for neural networks

2023-08-27 · Marcelo Forets, Christian Schilling

We study the problem of computing the preimage of a set under a neural network with piecewise-affine activation functions. We recall an old result that the preimage of a polyhedral set is again a union of polyhedral sets…