CoLA: Convolutional Neural Network Model for Secure Low Overhead Logic Locking Assignment

CoLA: Convolutional Neural Network Model for Secure Low Overhead Logic Locking Assignment
复制标题

CoLA:用于安全低开销逻辑锁定分配的卷积神经网络模型

DOI:
10.1145/3583781.3590219
复制
发表时间:
2023
期刊:
Proceedings of Great Lakes Symposium on VLSI (GLSVLSI
影响因子:
--
通讯作者:
Rezaei, Amin
Rezaei, Amin
中科院分区:
--
文献类型:
--
作者:
Aghamohammadi, Yeganeh;Rezaei, Amin

文献摘要

参考文献

被引文献

相似文献

芯片设计人员可以通过使用逻辑锁定和模糊处理来保护他们的IC免受盗版和生产过剩的侵害。然而,有许多攻击可以在激活的IC的帮助下检查逻辑锁定的网表,并使用SAT解算器提取正确的密钥。此外,当涉及到制造时,施加的面积开销是一个挑战,需要仔细注意以保持设计目标。因此,要分配一种逻辑锁定方法,该方法可以提供针对各种攻击的安全性,同时增加最小的面积开销,需要对电路结构进行全面的了解。针对这一目标,本文首先构建了一个多标签数据集,通过对使用现有逻辑锁定方法和不同密钥大小锁定的基准测试运行不同的攻击来获取每个基准测试所提供的安全级别和开销。然后,我们提出并分析了COLA,这是一种卷积神经网络模型,它是在该数据集上训练的,因此能够通过分析提取的基准电路的特征来将电路映射到安全的低开销锁定方案。考虑到相同电路的不同重新合成版本,使可口可乐能够学习不仅仅是结构视图的特征。在对新的、不可见的数据进行分类时,我们使用了一种量化方法来降低特征提取的计算开销,从而加快了锁定分配过程。在10000多个数据上的结果表明,在训练和验证阶段都有很高的准确率。
Chip designers can secure their ICs against piracy and overproduction by employing logic locking and obfuscation. However, there are numerous attacks that can examine the logic-locked netlist with the assistance of an activated IC and extract the correct key using a SAT solver. In addition, when it comes to fabrication, the imposed area overhead is a challenge that needs careful attention to preserve the design goals. Thus, to assign a logic locking method that can provide security against diverse attacks and at the same time add minimal area overhead, a comprehensive understanding of the circuit structure is needed. Towards this goal, in this paper, we first build a multi-label dataset by running different attacks on benchmarks locked with existing logic locking methods and various key sizes to capture the provided level of security and overhead for each benchmark. Then we propose and analyze CoLA, a convolutional neural network model that is trained on this dataset and thus is able to map circuits to secure low-overhead locking schemes by analyzing extracted features of the benchmark circuits. Considering various resynthesized versions of the same circuits empowers CoLA to learn features beyond the structure view alone. We use a quantization method that can lower the computation overhead of feature extraction in the classification of new, unseen data, hence speeding up the locking assignment process. Results on over 10000 data show high accuracy both in the training and validation phases.
OMLA:基于无 Oracle 机器学习的逻辑锁定攻击
DOI: 10.1109/tcsii.2021.3113035
发表时间: 2022
期刊: IEEE Transactions on Circuits and Systems II: Express Briefs
影响因子: --
作者:
Lilas Alrahis;Satwik Patnaik;Muhammad Shafique;O. Sinanoglu
通讯作者: O. Sinanoglu
SigAttack:针对逻辑加密的新的基于 SAT 的高级攻击
DOI: 10.23919/date.2019.8714924
发表时间: 2019
期刊: Testing in Europe (DATE
影响因子: --
作者:
Shen, Yuanqi;Li, You;Kong, Shuyu;Rezaei, Amin;Zhou, Hai
通讯作者: Zhou, Hai
DOI: 10.1109/iccad.2017.8203759
发表时间: 2017-11
期刊: 2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
影响因子: --
作者:
H. Zhou;Ruifeng Jiang;Shuyu Kong
通讯作者: H. Zhou;Ruifeng Jiang;Shuyu Kong
通过锁定拯救后SAT时代的逻辑加密
DOI: 10.23919/date48585.2020.9116500
发表时间: 2020
期刊: Testing in Europe (DATE
影响因子: --
作者:
Rezaei, Amin;Shen, Yuanqi;Zhou, Hai
通讯作者: Zhou, Hai
DOI: 10.1145/3060403.3060469
发表时间: 2017-05
期刊: Proceedings of the Great Lakes Symposium on VLSI 2017
影响因子: --
作者:
Yuanqi Shen;H. Zhou
通讯作者: Yuanqi Shen;H. Zhou