Year: 2024
Type: conference-paper
Abstract: Hyperdimensional Computing (HDC), a promising alternative to address the limitations of edge devices, is not exempt from the security challenges confronted by machine learning algorithms, in particular, adversarial attacks. The limited body of research exploring the security implications of HDC overlooks its inherent algorithm. In this paper, we propose a novel and effective adversarial attack technique targeting HDC. Our approach analyzes and prioritizes the impact of input features as well as encoded elements on decision boundaries and perturbs the input towards incorrect decisions in a guided manner. We evaluate our method on different datasets and attack models (i.e., untargeted/targeted, white-box/gray-box). Experimental results indicate that our proposed design, HDXpose, significantly outperforms the state-of-the-art attack techniques by achieving higher success rate with smaller distortion and execution time, rendering its efficacy for real-time attack generation.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Funder: National Science Foundation
Awards: CAP: AI-Assisted Supervisory Control of Wind Farm Connection to the Grid for Stability Monitoring, FET: Small: Brain-Inspired Hyperdimensional Computing for IoT Applications, AI Institute for Learning-Enabled Optimization at Scale (TILOS), CC* NPEO: Toward the National Research Platform, Category II: A Prototype National Research Platform, IUCRC Phase I University of California, San Diego: Center for Power Management Integration (PMIC), Collaborative Research: MLWiNS: Hyperdimensional Computing for Scalable IoT Intelligence Beyond the Edge
OpenAlex ID: W4409285543