Work

Nonideality-aware training makes memristive networks more robust to adversarial attacks

Year: 2025

Type: article

Abstract: Neural networks are now deployed in a wide number of areas, from object classification to natural language systems. Implementations using analog devices such as memristors promise better power efficiency, potentially bringing these applications to a greater number of environments. However, such systems suffer from more frequent device faults, and overall, their exposure to adversarial attacks has not been studied extensively. In this work, we investigate how nonideality-aware training—a common technique to deal with physical nonidealities—affects adversarial robustness. We find that adversarial robustness is significantly improved, even with limited knowledge of what nonidealities will be encountered during test time.

Source: APL Machine Learning

DOI: 10.1063/5.0241202

Authors: Dovydas Joksas, Luis Muñoz-González, Emil Lupu, Adnan Mehonic

Institutions: University College London, Imperial College London

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: Royal Academy of Engineering, Engineering and Physical Sciences Research Council

Awards: G4469111166, Memory Impedance for Efficient Complex-valued Neural Networks