{
  "abstract": "Quantum computing undermines traditional public-key cryptosystems like RSA and ECC, prompting NIST to standardize Module Lattice Key Encapsulation Mechanism (ML-KEM) as a core Post-Quantum Cryptography (PQC) scheme in August 2024. Despite its theoretical security, ML-KEM’s practical vulnerability in embedded systems remains underexplored. This study evaluates ML-KEM on an ARM Cortex-M4 microcontroller under deep learning(DL)-based side-channel attacks (DL-SCA), revealing that a single power trace enables 32-byte message recovery with 99.98% accuracy, while cross-device testing across three chips achieves over 99% accuracy, highlighting critical DL-driven threats. To better understand the spectral characteristics exploited by deep-learning-based side-channel attacks, we conduct a controlled frequency-band sensitivity study using Butterworth and Chebyshev low-pass filters applied to recorded traces. Across different cutoff frequencies and filter orders, the validation accuracy decreases substantially under aggressive attenuation, indicating that a significant fraction of exploitable leakage resides in higher-frequency components. Rather than claiming that offline digital filtering constrains a realistic adversary, we interpret these results as evidence for where leakage-sensitive information is concentrated, thereby providing guidance for implementable countermeasures such as masking, shuffling, desynchronization, and acquisition-path power/EM conditioning in embedded PQC systems. This cost-efficient solution requires no algorithm/hardware modifications, emphasizing the urgency of implementation-level protections for secure PQC deployment in resource-constrained systems.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan",
    "Master’s Program of Information and Communication Security, Feng Chia University, Taichung, Taiwan"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Chung-Wei Kuo",
      "orcid": "0009-0006-0847-4966"
    },
    {
      "affs": [
        0
      ],
      "name": "Yu-I Hung"
    },
    {
      "affs": [
        0
      ],
      "name": "Kai-Lun Lin"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/45bfr03r8t00n.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0358974",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13734496/",
  "id": "45bfr03r8t00n",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0358974",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Algebra"
    ],
    [
      "heading",
      "Algorithms"
    ],
    [
      "heading",
      "Applied Mathematics"
    ],
    [
      "heading",
      "Artificial Intelligence"
    ],
    [
      "heading",
      "Butterworth Filters"
    ],
    [
      "heading",
      "Computer and Information Sciences"
    ],
    [
      "heading",
      "Cryptography"
    ],
    [
      "heading",
      "Deep Learning"
    ],
    [
      "heading",
      "Encryption"
    ],
    [
      "heading",
      "Engineering and Technology"
    ],
    [
      "heading",
      "Machine Learning"
    ],
    [
      "heading",
      "Mathematics"
    ],
    [
      "heading",
      "Physical Sciences"
    ],
    [
      "heading",
      "Polynomials"
    ],
    [
      "heading",
      "Research Article"
    ],
    [
      "heading",
      "Research and Analysis Methods"
    ],
    [
      "heading",
      "Signal Filtering"
    ],
    [
      "heading",
      "Signal Processing"
    ],
    [
      "heading",
      "Simulation and Modeling"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning/Deep learning"
    ],
    [
      "plos",
      "/Computer and information sciences/Cryptography"
    ],
    [
      "plos",
      "/Computer and information sciences/Cryptography/Encryption"
    ],
    [
      "plos",
      "/Engineering and technology/Signal processing"
    ],
    [
      "plos",
      "/Engineering and technology/Signal processing/Signal filtering"
    ],
    [
      "plos",
      "/Engineering and technology/Signal processing/Signal filtering/Butterworth filters"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Algebra/Polynomials"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Applied mathematics/Algorithms"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Cryptography"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Cryptography/Encryption"
    ],
    [
      "plos",
      "/Research and analysis methods/Simulation and modeling/Algorithms"
    ]
  ],
  "openalex": null,
  "pdf_url": null,
  "pmcid": "PMC13734496",
  "pmid": "42981314",
  "published": "2026-11-04",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/45bfr03r8t00n.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T12:20:11Z",
      "native_id": "10.1371/journal.pone.0358974",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0358974"
    },
    {
      "first_seen": "2026-11-08T12:24:00Z",
      "native_id": "PMC13734496",
      "source": "pmc",
      "url": "https://doi.org/10.1371/journal.pone.0358974"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "plos:algebra",
      "subfield": "algebra-number-theory"
    }
  ],
  "title": "Deep-learning side-channel analysis of embedded ML-KEM: Single-trace message recovery, cross-device generalization, and frequency-band leakage characterization",
  "title_text": "Deep-learning side-channel analysis of embedded ML-KEM: Single-trace message recovery, cross-device generalization, and frequency-band leakage characterization",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T12:24:00Z",
  "url": "https://research.draconitic.com/paper/45bfr03r8t00n",
  "venue": "PLOS One",
  "versions": []
}