CAD for Assurance of Electronic Systems


By: Dominik Sisejkovic (RWTH Aachen University), Farhad Merchant (RWTH Aachen University), Lennart M. Reimann (RWTH Aachen University), Harshit Srivastava (RWTH Aachen University), Ahmed Hallawa (RWTH Aachen University) and Rainer Leupers (RWTH Aachen University)

Stage: RTL, Gate-Level


SnapShot is an oracle-less attack on logic locking that utilizes machine learning/deep learning methods to extract (predict) the correct key out of a locked gate-level netlist (both combinational and sequential). Hereby, SnapShot can perform the prediction by just “looking” at the post-resynthesized netlist, without the need to reconstruct the pre-resynthesized design. The major aspects of SnapShot are as follows:

  • The attack is applicable without a golden reference.
  • The attack flow can be adapted to any logic locking scheme. Note that, in principle, SnapShot can be applied to multiple design levels (e.g., RTL, gate-level or even layout).
  • SnapShot has a linear time complexity with respect to the key length.
  • Any machine learning/deep learning model can be used inside SnapShot for attack exploration.


Dominik Sisejkovic

Input/Output Interface

  • Input: Logic locked post-resynthesized gate-level netlist
  • Output: Predicted activation key bits


Synthesis tool (e.g., Synopsys DC)

Licensing Info

For now: the tool is not yet available online


Sisejkovic, Dominik; Merchant, Farhad; Reimann, Lennart M; Srivastava, Harshit; Hallawa, Ahmed; Leupers, Rainer

Challenging the Security of Logic Locking Schemes in the Era of Deep Learning: A Neuroevolutionary Approach Journal Article

In: J. Emerg. Technol. Comput. Syst., vol. 17, no. 3, 2021, ISSN: 1550-4832.

Abstract | Links | BibTeX