arXiv subjects

Yooshin Kim

Publications and source records attributed to Yooshin Kim.

3 recordsLinked to original sources

arXiv2026

Tracing the Origins: Legacy Codec Identification in Neural Audio Transcoding

Residual Vector Quantization (RVQ)-based neural audio codecs (NACs) enable high-fidelity audio distribution at unprecedentedly low bitrates through discrete token-based representations. However, this shift disrupts traditional forensics, as non-linear neural transcoding obscures the underlying traces of legacy compression. This study defines the forensic gap and proposes a Transformer-based framework designed to leverage the hierarchical and temporal dependencies inherent in RVQ sequences. By modeling inter-layer causal relationships and dynamic forensic significance, our model effectively disentangles superimposed artifacts from legacy-to-neural transcoding. Experimental results achieve 97%+ accuracy for codec identification and robust joint identification performance across 32-128 kbps. These results demonstrate that traditional codec traces persist even after neural transcoding, supporting the feasibility and necessity of neural-codec-aware audio forensics.

cs.SD↗

arXiv2026

System-aware contextual digital twin for ICS anomaly diagnosis

Industrial Control Systems (ICS) integrate computing, physical processes, and communication to operate critical infrastructures such as power grids, water treatment plants, and oil and gas facilities. As ICS become increasingly targeted by cyberattacks, timely and reliable anomaly diagnosis is essential for protecting operational safety. However, existing ICS anomaly detection approaches face practical limitations: supervised methods require extensive labeled attack data and suffer from class imbalance, while model-based detectors often lack the ability to provide deep insight into the root causes of anomalies, leading to elevated false alarms and making it difficult for operators to initiate a timely response. In this work, we propose a system-aware unsupervised framework for ICS anomaly diagnosis that combines lightweight online detection with contextual explanation. The system identifies deviations from observed normal behaviors without prior knowledge of system topology. To support actionable response, we further concatenate a contextual digital twin augmented with an Large Language Model (LLM) to enhance interpretability, which translates detection evidence into grounded diagnostic hypotheses and verification steps for operators. Experiments on public ICS benchmarks demonstrate that the proposed framework achieves real-time detection efficiency and provides consistent, interpretable anomaly diagnoses, enabling low-latency warning and practical deployment in complex industrial environments.

cs.CR↗

arXiv2024

KDPrint: Passive Authentication using Keystroke Dynamics-to-Image Encoding via Standardization

In contemporary mobile user authentication systems, verifying user legitimacy has become paramount due to the widespread use of smartphones. Although fingerprint and facial recognition are widely used for mobile authentication, PIN-based authentication is still employed as a fallback option if biometric authentication fails after multiple attempts. Consequently, the system remains susceptible to attacks targeting the PIN when biometric methods are unsuccessful. In response to these concerns, two-factor authentication has been proposed, albeit with the caveat of increased user effort. To address these challenges, this paper proposes a passive authentication system that utilizes keystroke data, a byproduct of primary authentication methods, for background user authentication. Additionally, we introduce a novel image encoding technique to capture the temporal dynamics of keystroke data, overcoming the performance limitations of deep learning models. Furthermore, we present a methodology for selecting suitable behavioral biometric features for image representation. The resulting images, depicting the user's PIN input patterns, enhance the model's ability to uniquely identify users through the secondary channel with high accuracy. Experimental results demonstrate that the proposed imaging approach surpasses existing methods in terms of information capacity. In self-collected dataset experiments, incorporating features from prior research, our method achieved an Equal Error Rate (EER) of 6.7%, outperforming the existing method's 47.7%. Moreover, our imaging technique attained a True Acceptance Rate (TAR) of 94.4% and a False Acceptance Rate (FAR) of 8% for 17 users.

cs.CR↗