Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3002755

Adaptive anomaly detection for identifying attacks in cyber-physical systems: A systematic literature review

Moriano, Pablo [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (ORCID:0000000218228885)·Hespeler, Steven C. [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (ORCID:0000000349839651)·Li, Mingyan [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)]·Mahbub, Maria [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (ORCID:0000000234229650)
View original source ↗Read source document ↗Export metadata ↓

Abstract

Modern cyberattacks in cyber-physical systems (CPS) rapidly evolve and cannot be deterred effectively with most current methods, which focus on characterizing past threats. Adaptive anomaly detection (AAD) is among the most promising techniques to detect evolving cyberattacks, with an emphasis on fast data processing and model adaptation. AAD has been researched extensively; however, to the best of our knowledge, our work is the first systematic literature review (SLR) on current research in this field. We present a comprehensive SLR, gathering 397 relevant papers and systematically analyzing 65 of them (47 research and 18 survey papers) on AAD in CPS from 2013 to November 2023. We introduce a novel taxonomy considering attack types, CPS application, learning paradigm, data management, and algorithms. Our findings show that most studies addressed either model adaptation or data processing, but rarely both simultaneously. This indicates a research gap in fully adaptive solutions. We also categorize algorithms, datasets, and attack characteristics, and summarize strengths and weaknesses across the literature. Our review provides a structured and accessible reference for researchers and practitioners, offering insights into key trends and highlighting limitations in current approaches. Finally, we outline several future research directions, including the need for integrated real-time processing and adaptive learning, explainability, and uncertainty quantification in AAD for CPS.

Explore related subjects

AdaptationAdaptive ImmunityAdaptive clinical trialAnomaly detectionComputational IntelligenceCyber-Physical SystemsCybersecurityMotion DetectionStochastic Learning and Adaptive Control

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Moriano, Pablo [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (ORCID:0000000218228885), Hespeler, Steven C. [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (ORCID:0000000349839651), Li, Mingyan [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)], Mahbub, Maria [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (ORCID:0000000234229650). 2025-06-23. Adaptive anomaly detection for identifying attacks in cyber-physical systems: A systematic literature review. https://doi.org/10.1007/s10462-025-11292-w

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2024

Discovery and adaptation of microbes that degrade oxidized low-density polyethylene films

There is a growing interest in developing a methodology for effectively cleaving carbon–carbon (C–C) bonds in polymer backbones through bioconversion processes that utilize microorganisms and their enzymes. This upsurge of interest is driven by the goal of achieving a circular economy. Polyolefin post-consumer plastics are a substantial source of carbon, but the recycling potential is severely limited. Upcycling routes are needed for converting polyolefin post-consumer plastics into value-added products while concurrently mitigating adverse environmental effects. These materials contain carbon-based chemicals that can, in principle, serve as the feedstock for microbial metabolism. Some microbes have been reported to grow on polyolefin plastics, but the rate of biodegradation is insufficient for industrial processes. In this study, low-density polyethylene (LDPE) films were subjected to two mild ozone-based oxidation treatments, which facilitated biodegradation. The degree of oxidation was determined by Fourier transform infrared spectroscopy via analysis of the carbonyl index (1,710/1,460 cm −1 ), which ranged from 0.3 to 2.0, and also via analysis of the carboxylic acid content. Following oxidation of the films, studies were conducted to investigate the ability of a panel of polyvinyl alcohol-degrading microbes to degrade the oxidized films. A defined minimal medium was used to cultivate and assess microbial growth on the oxidized films. Following 45 days of cultivation, the most effective strains were further cultivated up to three additional generations on the oxidized film substrates to improve their ability to degrade the oxidized LDPE films. After these enrichments, we identified a strain from the third generation of Pseudomonas sp. Rh926 that exhibited significant cell growth and reduced the oxidized LDPE film mass by 25% in 30 days, demonstrating an enhanced capacity for degrading the oxidized LDPE films.

Adaptation↗