Close

Presentation

HDTest: Differential Fuzz Testing of Brain-Inspired Hyperdimensional Computing
Time
Location
Event Type
Research Manuscript
Virtual Programs
Hosted in Virtual Platform
Keywords
Emerging Models of Computation
Topics
Design
DescriptionBrain-inspired hyperdimensional computing (HDC) is an emerging computational paradigm that mimics brain cognition and leverages hyperdimensional vectors with fully distributed holographic representation and (pseudo)randomness. In this paper, we design, implement and evaluate HDTest, the first testing framework to systematically test HDC model by automatically exposing unexpected or incorrect behaviors under rare inputs. Guided by the distance between query hypervector and reference hypervector in HDC, we continuously mutate original inputs to generate new inputs that can trigger incorrect behaviors of HDC model. On average, HDTest can generate around 400 adversarial inputs within one minute running on a commodity computer.