English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Logic locking has been proposed to safeguard intellectual property (IP)during chip fabrication. Logic locking techniques protect hardware IP by makinga subset of combinational modules in a design dependent on a secret key that iswithheld from untrusted parties. If an incorrect secret key is used, a set ofdeterministic errors is produced in locked modules, restricting unauthorizeduse. A common target for logic locking is neural accelerators, especially asmachine-learning-as-a-service becomes more prevalent. In this work, we explorehow logic locking can be used to compromise the security of a neuralaccelerator it protects. Specifically, we show how the deterministic errorscaused by incorrect keys can be harnessed to produce neural-trojan-stylebackdoors. To do so, we first outline a motivational attack scenario where acarefully chosen incorrect key, which we call a trojan key, producesmisclassifications for an attacker-specified input class in a lockedaccelerator. We then develop a theoretically-robust attack methodology toautomatically identify trojan keys. To evaluate this attack, we launch it onseveral locked accelerators. In our largest benchmark accelerator, our attackidentified a trojan key that caused a 74\% decrease in classification accuracyfor attacker-specified trigger inputs, while degrading accuracy by only 1.7\%for other inputs on average.

Exploiting Logic Locking for a Neural Trojan Attack on Machine Learning Accelerators