An optical anti-counterfeit detection method for semiconductor devices has proven to be more robust than existing techniques.
The deep-learning approach, called ‘Residual, Attention-based Processing of Tampered Optical Responses’ (Raptor), hopes to disrupt the $75 billion counterfeit chip market by detecting tampering through analysing gold nanoparticle patterns embedded on chips.
Chips shortage gives rise to counterfeit chips
A profound shortage of new chips and a surge of counterfeit chips, has introduced substantial risks of malfunction and unwanted surveillance in the semiconductor industry.
In particular, the latter inadvertently gives rise to a $75 billion counterfeit chip market that jeopardises safety and security across multiple sectors dependent on semiconductor technologies, such as aviation, communications, quantum, artificial intelligence, and personal finance.
Several techniques aimed at affirming semiconductor authenticity have been introduced by previous researchers to detect counterfeit chips, largely leveraging physical security tags baked into the chip functionality or packaging. Central to many of these methods are physical unclonable functions (PUFs), which are unique physical systems that are difficult to replicate either because of economic constraints or inherent physical properties.
Rather than being grounded in cryptographic hardness, PUFs emphasise the economic and technological challenges of duplicating a given system’s physical characteristics. Optical PUFs, which capitalise on the distinct optical responses of random media, are especially promising.
Optical PUFs are easy to fabricate and quick to measure, making them ideal for proof-of-concept tampering identification experiments. Nano-scale metallic optical systems have especially been rising in popularity due to their strong scattering response at optical wavelengths, increasing robustness during post-tampering measurements.
However, achieving scalability and maintaining accurate discrimination between adversarial tampering and natural degradation, such as physical ageing at higher temperatures, packaging abrasions, and humidity impact, pose significant challenges.
AI optical approach outperforms existing optical methods
The new method, developed at Purdue University in the US, can identify adversarial tampering features such as malicious package abrasions, compromised thermal treatment, and adversarial tearing.
The team first built a 10,000-image dataset of randomly distributed gold nanoparticles by augmenting original images from the dark-field microscope. Next, with nanoparticle pattern pixel regions clustered into local particle patterns, their centres of mass are extracted. Finally, the Distance matrix PUFs are generated by evaluating all pairwise distances between these nanoparticle patterns.
To test anticounterfeit capabilities, tampering behaviour in nanoparticle PUFs was simulated, considering both natural changes and malicious adversarial tampering. Raptor, using an attention mechanism, prioritises nanoparticle correlations across pre-tamper and post-tamper samples before feeding them into a residual, attention-based deep convolutional classifier.
Raptor correctly detected tampering in 97.6% of distance matrices under worst-case tampering scenarios, outperforming previous methods (Hausdorff, Procrustes, Average Hausdorff Distance) by 40.6%, 37.3%, and 6.4%, respectively.
This work applied attention mechanisms for deep learning-assisted PUFs authentication. It achieved high verification accuracy under difficult, real-world tampering schema, which opens a large opportunity for the adoption of deep learning-based anti-counterfeit methods in the semiconductor industry.
The research was recently published in Advanced Photonics.
Credit for main image: Shutterstock/Cristian Storto
