Discerning Limitations of GNN-based Attacks on Logic Locking

被引：3

作者：

Darjani, Armin ^{[1
]}

Kavand, Nima ^{[1
]}

Rai, Shubham ^{[1
]}

Kumar, Akash ^{[1
]}

机构：

[1] Tech Univ Dresden, Chair Processor Design, CFAED, Dresden, Germany

来源：

2023 60TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, DAC | 2023年

关键词：

Logic locking; Structural attacks; ML-based; GNN;

D O I：

10.1109/DAC56929.2023.10247847

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Machine learning (ML)-based attacks have revealed the possibility of utilizing neural networks to break locked circuits without needing functional chips (Oracle). Among ML approaches, GNN (graph neural networks)-based attacks are the most potent tools that attackers can employ as they exploit graph structures inherent to a circuit's netlist. Although promising, in this paper, we reveal that GNNs have some impediments in attacking locked circuits. We investigate the limits of the state-of-the-art GNN-based attacks against logic locking and show that we can drastically decrease the accuracy of these attacks by utilizing these limitations in the locking process.

引用

页数：6

共 50 条

[41] SAT Based Partial Attack on Compound Logic Locking [J].

John, Melbin ;

Hoda, Aadil ;

Chouksey, Ramanuj ;

Karfa, Chandan .

PROCEEDINGS OF THE 2020 ASIAN HARDWARE ORIENTED SECURITY AND TRUST SYMPOSIUM (ASIANHOST), 2020,

[42] StateLock: State Transition Based Logic Locking for Sequential Circuits [J].

Kasarabada, Yasaswy ;

Vemuri, Ranga .

2020 33RD INTERNATIONAL CONFERENCE ON VLSI DESIGN AND 2020 19TH INTERNATIONAL CONFERENCE ON EMBEDDED SYSTEMS (VLSID), 2020, :171-176

[43] Truly Stripping Functionality for Logic Locking: A Fault-Based Perspective [J].

Sengupta, Abhrajit ;

Nabeel, Mohammed ;

Limaye, Nimisha ;

Ashraf, Mohammed ;

Sinanoglu, Ozgur .

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2020, 39 (12) :4439-4452

[44] SCOPE: Synthesis-Based Constant Propagation Attack on Logic Locking [J].

Alaql, Abdulrahman ;

Rahman, Md Moshiur ;

Bhunia, Swarup .

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2021, 29 (08) :1529-1542

[45] On the Efficacy and Vulnerabilities of Logic Locking in Tree-Based Machine Learning [J].

de Abreu, Brunno Alves ;

Paim, Guilherme ;

Alrahis, Lilas ;

Flores, Paulo ;

Sinanoglu, Ozgur ;

Bampi, Sergio ;

Amrouch, Hussam .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2025, 72 (01) :180-191

[46] A Novel Security Assessment Method Based on Linear Regression for Logic Locking [J].

Tsai, I-Chun ;

Zhong, Yi ;

Liu, Fang-Ru ;

Feng, Jianhua .

2019 IEEE INTERNATIONAL CONFERENCE ON ELECTRON DEVICES AND SOLID-STATE CIRCUITS (EDSSC), 2019,

[47] A Novel Probability-Based Logic-Locking Technique: ProbLock [J].

Yue, Michael ;

Tehranipoor, Sara .

SENSORS, 2021, 21 (23)

[48] ATPG-Based Cost-Effective, Secure Logic Locking [J].

Sengupta, Abhrajit ;

Nabeel, Mohammed ;

Yasin, Muhammad ;

Sinanoglu, Ozgur .

2018 IEEE 36TH VLSI TEST SYMPOSIUM (VTS 2018), 2018,

[49] Boolean Domain Attack on Corrupt and Correct Based Logic Locking Techniques [J].

Madera, Joseph ;

Juretus, Kyle .

PROCEEDING OF THE GREAT LAKES SYMPOSIUM ON VLSI 2024, GLSVLSI 2024, 2024, :415-420

[50] DeepAttack: A Deep Learning Based Oracle-less Attack on Logic Locking [J].

Raj, Anand ;

Avula, Nikhitha ;

Das, Pabitra ;

Sisejkovic, Dominik ;

Merchant, Farhad ;

Acharyya, Amit .

2023 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS, 2023,

← 1 2 3 4 5 →