Tree-based machine learning models have limitations that despite their strong forecasting performance, they are vulnerable to extrapolation outside the distribution of data with a trend. To address this issue, this study proposes a two-step forecasting procedure in which the machine learning model is applied to the residuals after removing the trend from the time series. First, the global nonlinear trend component is separated through regression, and the residuals are extracted which may include autocorrelation and seasonality. After that, the residuals are modeled using Random Forest or XGBoost which are tree-based machine learning models. In the last forecasting step, the separated nonlinear trend is recombined. The simulation experiment uses data from the M3 and M4 competition data and compares the proposed method with a standalone machine learning model without the trend adjustment to evaluate performance. This study proposes a method to combine trend decomposition with machine learning models for time series forecasting and discusses how effective it can enhance forecasting accuracy and computation effciency.

Recent advances in audio generation have increased the risk of realistic environmental sound manipulation, motivating the ESDD 2026 Challenge as the first large-scale benchmark for Environmental Sound Deepfake Detection (ESDD). We propose BEAT2AASIST which extends BEATs-AASIST by splitting BEATs-derived representations along frequency or channel dimension and processing them with dual AASIST branches. To enrich feature representations, we incorporate top-k transformer layer fusion using concatenation, CNN-gated, and Squeeze-and-Excitation (SE)-gated strategies. In addition, vocoder-based data augmentation is applied to improve robustness against unseen spoofing methods. Experimental results on the official test sets demonstrate that the proposed approach achieves competitive performance across the challenge tracks.

Recent advances in audio generation have increased the risk of realistic environmental sound manipulation, motivating the ESDD 2026 Challenge as the first large-scale benchmark for Environmental Sound Deepfake Detection (ESDD). We propose BEAT2AASIST which extends BEATs-AASIST by splitting BEATs-derived representations along frequency or channel dimension and processing them with dual AASIST branches. To enrich feature representations, we incorporate top-k transformer layer fusion using concatenation, CNN-gated, and Squeeze-and-Excitation (SE)-gated strategies. In addition, vocoder-based data augmentation is applied to improve robustness against unseen spoofing methods. Experimental results on the official test sets demonstrate that the proposed approach achieves competitive performance across the challenge tracks.

Sound Event Detection (SED) systems are essential for understanding and classifying the causes and temporal occurrences of sounds in diverse environments. This paper introduces a robust and efficient SED system that integrates a novel Frequency-aware Lightweight Convolutional Attention Module (FLCAM) and semi-supervised learning techniques to address key challenges in audio analysis. The FLCAM enhances 2D convolutional models by preserving critical frequency-domain features and adaptively assigning attention weights, enabling superior performance while maintaining computational efficiency. To fully leverage strongly labeled, weakly labeled, and unlabeled data, our system employs the Mean Teacher framework, which ensures consistency between predictions under different augmentations. Comprehensive experiments on the DESED and L3DAS22 datasets demonstrate the effectiveness of our approach, achieving improvements of approximately 9 percentage points in PSDS and 2 percentage points in F-score metrics, respectively. Despite utilizing significantly fewer parameters, the proposed SED system achieves performance comparable to state-of-the-art models, making it suitable for real-world applications, including resource-constrained environments.

은닉 마르코프 모형(hidden markov model; HMM)은 통계적 모형 기반의 비지도학습 방법 중 하나이다. HMM은 은닉 상태의 수를 조절하여 스퀀스 데이터에 대해 학습이 가능하다. 이 논문에서는 자기상관이 존재하는 공정에서 HMM에 기반한 공정 모니터링 절차를 소개하고, 은닉 상태의 수를 다르게 설정하여 절차의 성능을 비교하고 평가하였다. 성능 평가를 위해 평균 런길이(average run length; ARL)와 다양한 변화에 대한 상대적인 성능 비교를 위해 RMI (relative mean index)라는 측도를 사용하였다. 모의실험을 통해 은닉 상태의 수에 따른 성능 변화 및 딥러닝 기반 절차 중 하나인 RNN 기반 잔차 관리도 절차와 성능을 비교하였다. 시계열 모형의 자기상관 구조와 변화 유형에 따라 HMM 기반 절차의 최적의 은닉 상태의 수는 다르게 나타났으며, AR 형태의 과정에서 1차 자기상관이 아주 강한 경우 HMM 기반 절차가 RNN 기반 절차에 비해 전반적으로 좋은 성능을 보임을 알 수 있었다.

In real-world applications, anomaly detection tasks are critically important. For example, fraud detection for the financial domains and the diagnosis of diseases for the medical domains require highly accurate predictions, as errors can lead to severe consequences. These tasks often rely on sensitive personal data, making it necessary to apply privacy-preserving techniques. However, applying privacy-preserving techniques directly degrades performance. To mitigate this issue, the minority class in an imbalanced dataset can be upsampled to improve balance. In this paper, we propose a differentially private upsampling method using a kernel-based support function for imbalanced datasets. The proposed method employs kernel support vector domain description to estimate the distribution of minority class data under differential privacy constraints, generating synthetic instances based on gradient methods. Additionally, we propose a filtering process that leverages the support function of the majority class data to refine the generated samples without additional privacy loss. Experimental results on real-world datasets demonstrate that the proposed method maintains robust privacy guarantees and achieves superior performance in minority class metrics, comparable to non-private methods.Co-authors: Yujin Choi, Jinseong Park, Youngjoo Park, Jaewook Lee

In IoT-enabled industrial environments, ensuring the privacy and security of operational data is paramount for fault diagnosis systems. This study presents a novel framework that seamlessly integrates homomorphic encryption (HE) with deep learning to achieve secure and efficient fault diagnosis for industrial bearings. By performing computations directly on encrypted sensor data, the framework guarantees full data confidentiality throughout the diagnostic process without requiring decryption. Key technical contributions of this work include the development of a minimax polynomial approximation for ReLU activations, which enhances diagnostic accuracy while preserving efficiency, and the design of an efficient 1D convolution method that combines two existing HE convolution techniques for optimal performance. Additionally, the framework incorporates frequency-domain optimizations using the Discrete Fourier Transform (DFT), which significantly enhance processing efficiency. The proposed model was trained on the CWRU bearing dataset and validated on a private dataset, achieving a diagnostic accuracy of 95.92%, comparable to state-of-the-art models operating on plaintext data. Furthermore, the DFT-based optimizations reduced inference time by nearly threefold while maintaining superior accuracy, underscoring the framework’s potential to provide secure and efficient fault diagnosis for industrial applications.Co-authors: Hoki Kim, Youngdoo Son

Privacy-Preserving Deep Learning (PPDL) has been successfully applied in the inference phase to preserve the privacy of input data. However, PPDL models are vulnerable to model extraction attacks, in which an adversary attempts to steal the trained model itself. In this paper, we propose a new defense method against model extraction attacks that is specifically designed for PPDL based on secure multi-party computations and homomorphic encryption. The proposed method confounds inference queries for out-of-distribution data by using a fake network with the target network while optimizing computational efficiency for PPDL environments. Furthermore, we introduce Wasserstein regularization to ensure that the fake network’s output distribution is indistinguishable from the target network, thwarting adversaries’ attempts to discern any discrepancies within the PPDL framework. The experimental results demonstrate that our defense method attains a good accuracy-security trade-off and is effective against a wide range of attacks, including adaptive attacks and transfer attacks. Our work contributes to the field of PPDL by providing an extended perspective to improve the algorithm’s security and reliability beyond privacy.Co-authors: Yujin Choi, Jaewook Lee, Saerom Park

In real-world applications, anomaly detection tasks are critically important. For example, fraud detection for the financial domains and the diagnosis of diseases for the medical domains require highly accurate predictions, as errors can lead to severe consequences. These tasks often rely on sensitive personal data, making it necessary to apply privacy-preserving techniques. However, applying privacy-preserving techniques directly degrades performance. To mitigate this issue, the minority class in an imbalanced dataset can be upsampled to improve balance. In this paper, we propose a differentially private upsampling method using a kernel-based support function for imbalanced datasets. The proposed method employs kernel support vector domain description to estimate the distribution of minority class data under differential privacy constraints, generating synthetic instances based on gradient methods. Additionally, we propose a filtering process that leverages the support function of the majority class data to refine the generated samples without additional privacy loss. Experimental results on real-world datasets demonstrate that the proposed method maintains robust privacy guarantees and achieves superior performance in minority class metrics, comparable to non-private methods.Co-authors: Yujin Choi, Jaewook Lee