The Industrial Internet of Things (IIoT) is a physical information system developed based on traditional industrial control networks. As one of the most critical infrastructure systems, IIoT is also a preferred target for adversaries engaged in advanced persistent threats (APTs). To address this issue, we explore a deep-learning-based proactive APT detection scheme in IIoT. In this scheme, considering the characteristics of long attack sequences and long-term continuous APT attacks, our solution adopts a well-known deep learning model, bidirectional encoder representations from transformers (BERT), to detect APT attack sequences. The APT attack sequence is also optimized to ensure the model's long-term sequence judgment effectiveness. The experimental results not only show that the proposed deep learning method has feasibility and effectiveness for APT detection, but also certify that the BERT model has better accuracy and a lower false alarm rate when detecting APT attack sequences than other time series models.

In this work, we report the facile, environmentally friendly, room-temperature (RT) synthesis of porous CuO nanosheets and their application as a photocatalyst to degrade an organic pollutant/food dye using NaBH₄ as the reducing agent in an aqueous medium. Ultrahigh-resolution field effect scanning electron microscopy images of CuO displayed a broken nanosheet-like (a length of ∼160 nm, a width of ∼65 nm) morphology, and the lattice strain was estimated to be ∼1.24 × 10^–3 using the Williamson–Hall analysis of X-ray diffraction plots. Owing to the strong quantum size confinement effect, CuO nanosheets resulted in an optical energy band gap of ∼1.92 eV, measured using Tauc plots of the ultraviolet–visible (UV–vis) spectrum, resulting in excellent photocatalytic efficiency. The RT synthesized CuO catalyst showed a high Brunauer–Emmet–Teller surface area of 30.88 ± 0.2313 m²/g (a correlation coefficient of 0.99972) with an average Barrett–Joyner–Halenda pore size of ∼20.385 nm. The obtained porous CuO nanosheets exhibited a high crystallinity of 73.5% with a crystallite size of ∼12 nm and was applied as an efficient photocatalyst for degradation of the organic pollutant/food dye, Allura Red AC (AR) dye, as monitored by UV–vis spectrophotometric analysis and evidenced by a color change from red to colorless. From UV–vis spectra, CuO nanosheets exhibited an efficient and ultrafast photocatalytic degradation efficiency of ∼96.99% for the AR dye in an aqueous medium within 6 min at RT. According to the Langmuir–Hinshelwood model, photodegradation reaction kinetics followed a pseudo-first-order reaction with a rate constant of k = 0.524 min^–1 and a half-life (t_1/2) of 2.5 min for AR dye degradation in the aqueous medium. The CuO nanosheets showed an outstanding recycling ability for AR degradation and would be highly favorable and an efficient catalyst due to the synergistic effect of high adsorption capability and photodegradation of the food dye.