arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.11995cs.LG
收藏

二值化神经网络的网络反演

Network Inversion of Binarised Neural Nets

IIT Bombay(印度理工学院孟买分校)

Pirzada Suhail, Supratik Chakraborty, Amit Sethi

AI总结:

本文提出将训练好的二值化神经网络编码为CNF公式以实现推理与网络反演,为揭示黑盒性质和确保安全场景下的可信度提供新方法。

摘要:

尽管神经网络的部署取得了令人瞩目的成果,并在各种应用中日益普及,但其可解释性和理解仍是一个关键挑战。网络反演旨在从模型学习到的内部表示中重构输入空间,在揭示神经网络输入到输出映射的黑盒性质方面发挥着关键作用。在安全关键场景中,模型输出可能影响关键决策,相应输入空间的完整性至关重要,必须消除任何多余的“垃圾”以确保网络的可信度。二值化神经网络(BNNs)以二值权重和激活为特征,提供计算效率并降低内存需求,使其适用于资源受限的环境。本文提出了一种新方法,通过将训练好的BNN编码为捕获网络结构的CNF公式,实现推理和反演。

英文摘要:

While the deployment of neural networks, yielding impressive results, becomes more prevalent in various applications, their interpretability and understanding remain a critical challenge. Network inversion, a technique that aims to reconstruct the input space from the model's learned internal representations, plays a pivotal role in unraveling the black-box nature of input to output mappings in neural networks. In safety-critical scenarios, where model outputs may influence pivotal decisions, the integrity of the corresponding input space is paramount, necessitating the elimination of any extraneous "garbage" to ensure the trustworthiness of the network. Binarised Neural Networks (BNNs), characterized by binary weights and activations, offer computational efficiency and reduced memory requirements, making them suitable for resource-constrained environments. This paper introduces a novel approach to invert a trained BNN by encoding it into a CNF formula that captures the network's structure, allowing for both inference and inversion.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑