Non-intrusive Load Monitoring (NILM) algorithms, commonly referred to as load
disaggregation algorithms, are fundamental tools for effective energy
management. Despite the success of deep models in load disaggregation, they
face various challenges, particularly those pertaining to privacy and security.
This paper investigates the sensitivity of prominent deep NILM baselines to
adversarial attacks, which have proven to be a significant threat in domains
such as computer vision and speech recognition. Adversarial attacks entail the
introduction of imperceptible noise into the input data with the aim of
misleading the neural network into generating erroneous outputs. We investigate
the Fast Gradient Sign Method (FGSM), a well-known adversarial attack, to
perturb the input sequences fed into two commonly employed CNN-based NILM
baselines: the Sequence-to-Sequence (S2S) and Sequence-to-Point (S2P) models.
Our findings provide compelling evidence for the vulnerability of these models,
particularly the S2P model which exhibits an average decline of 20\% in the
F1-score even with small amounts of noise. Such weakness has the potential to
generate profound implications for energy management systems in residential and
industrial sectors reliant on NILM models.

对深度非侵入式负荷监测（NILM）基线模型进行敏感性研究，揭示常用 CNN-based NILM 模型在面对 Fast Gradient Sign Method 等对抗攻击时的脆弱性及其对能源管理系统的潜在影响。