Shaofeng Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shaofeng Tan has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Lisha Shuai
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
2 shared publications - Nan Zhang
State Grid Information and Telecommunication Group Company Ltd., Beijing, China
2 shared publications - Xiaolong Yang
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
2 shared publications - Gaoya Dong
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
1 shared publication Haokun Zhang
1 shared publication- Haokun Zhang
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 13 August 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Risk Prediction for Incident Chronic Disease and Comorbidity Using Outpatient Electronic Medical Records: Model Development and Temporal External Validation (Preprint)
BACKGROUND Research on the prediction of chronic comorbidity has mostly concentrated on disease transitions that occur after diagnosis, that is secondary prevention, whereas the outpatient period that precedes the first confirmed diagnosis is the critical window for primary prevention. This window presents several distinct difficulties, including sparse data, a systematic gap between recorded trajectories and true disease onset, and a distortion of probability calibration under class imbalance. OBJECTIVE This study examines whether a model that combines reference-range deviation (RD) encoding with a landmark design can achieve primary-prevention risk prediction for hypertension (HTN), diabetes mellitus (DM), and their comorbidity in an outpatient population, and whether the resulting performance transfers across time. METHODS Using an outpatient cohort collected between 2023 and 2024 (N = 401,569), we set 2024-01-01 as the landmark, adopt a one-year follow-up window, and construct three primary-prevention tasks defined as incident HTN, incident DM, and the incident co-occurrence of both diseases. Modeling is performed with the reference-range deviation multi-modal stacking (RD-MMS) framework, and external temporal validation is conducted on an independent cohort that has no patient overlap and is anchored at a 2025 landmark. Performance and clinical utility are assessed with the area under the receiver operating characteristic curve (AUROC), the expected calibration error (ECE), SHapley Additive exPlanations (SHAP), and decision curve analysis (DCA). RESULTS In internal five-fold cross-validation, the three tasks reach an AUROC of 0.818 for HTN, 0.774 for DM, and 0.839 for both diseases, each of which is significantly higher than the strongest single-modality baseline (p < 0.001). In external temporal validation, discrimination remains highly stable, with ΔAUROC within ±0.012, whereas probability calibration drifts under the downsampled prior; this drift is corrected by a lightweight recalibration step. SHAP shows that age is the dominant driver, with a contribution of 58.9% to 70.7%, yet laboratory, text, and visit-behavior features provide incremental discrimination beyond age, so that the model still significantly outperforms the minimal demographic baseline within a single age band (p < 0.05). The contribution of imaging text is close to zero, and a reduced model of 50 dimensions preserves performance with almost no loss. DCA confirms a positive clinical net benefit across the threshold range from 0.01 to 0.50. CONCLUSIONS The combination of a landmark design and RD encoding enables primary-prevention risk stratification for chronic comorbidity. By integrating age, laboratory trajectories, and visit patterns, the method achieves individualized risk refinement within a single age band, and it shows a general deployment pattern in which discrimination transfers across time while probability requires only a lightweight local recalibration.
- 13 August 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessRisk Prediction for Incident Chronic Disease and Comorbidity Using Outpatient Electronic Medical Records: Model Development and Temporal External Validation (Preprint)
BACKGROUND Research on the prediction of chronic comorbidity has mostly concentrated on disease transitions that occur after diagnosis, that is secondary prevention, whereas the outpatient period that precedes the first confirmed diagnosis is the critical window for primary prevention. This window presents several distinct difficulties, including sparse data, a systematic gap between recorded trajectories and true disease onset, and a distortion of probability calibration under class imbalance. OBJECTIVE This study examines whether a model that combines reference-range deviation (RD) encoding with a landmark design can achieve primary-prevention risk prediction for hypertension (HTN), diabetes mellitus (DM), and their comorbidity in an outpatient population, and whether the resulting performance transfers across time. METHODS Using an outpatient cohort collected between 2023 and 2024 (N = 401,569), we set 2024-01-01 as the landmark, adopt a one-year follow-up window, and construct three primary-prevention tasks defined as incident HTN, incident DM, and the incident co-occurrence of both diseases. Modeling is performed with the reference-range deviation multi-modal stacking (RD-MMS) framework, and external temporal validation is conducted on an independent cohort that has no patient overlap and is anchored at a 2025 landmark. Performance and clinical utility are assessed with the area under the receiver operating characteristic curve (AUROC), the expected calibration error (ECE), SHapley Additive exPlanations (SHAP), and decision curve analysis (DCA). RESULTS In internal five-fold cross-validation, the three tasks reach an AUROC of 0.818 for HTN, 0.774 for DM, and 0.839 for both diseases, each of which is significantly higher than the strongest single-modality baseline (p < 0.001). In external temporal validation, discrimination remains highly stable, with ΔAUROC within ±0.012, whereas probability calibration drifts under the downsampled prior; this drift is corrected by a lightweight recalibration step. SHAP shows that age is the dominant driver, with a contribution of 58.9% to 70.7%, yet laboratory, text, and visit-behavior features provide incremental discrimination beyond age, so that the model still significantly outperforms the minimal demographic baseline within a single age band (p < 0.05). The contribution of imaging text is close to zero, and a reduced model of 50 dimensions preserves performance with almost no loss. DCA confirms a positive clinical net benefit across the threshold range from 0.01 to 0.50. CONCLUSIONS The combination of a landmark design and RD encoding enables primary-prevention risk stratification for chronic comorbidity. By integrating age, laboratory trajectories, and visit patterns, the method achieves individualized risk refinement within a single age band, and it shows a general deployment pattern in which discrimination transfers across time while probability requires only a lightweight local recalibration.
- Open Access
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 4777-4794
PEEL: A Poisoning-Exposing Encoding Mechanism for Local Differential Privacy
Local Differential Privacy (LDP) has emerged as a dominant privacy paradigm in the Internet of Things (IoT) due to its lightweight, decentralized and scalable nature. However, the indistinguishability guarantee inherent to LDP mechanisms inadvertently masks adversarial manipulation, rendering poisoned data difficult to differentiate from legitimate perturbations. Existing poisoning defense mechanisms either incur prohibitive overheads incompatible with resource-constrained IoT devices or rely on rigid domain priors. To address this, we propose PEEL, a Poisoning-Exposing Encoding mechanism for LDP, which reformulates poisoning exposure as a geometric structural verification problem within the encoding subspace. Departing from probabilistic statistical filtering, PEEL exploits the rank disparity between legitimate sparse perturbations and arbitrary adversarial injections. By projecting LDP outputs onto a low-rank structural support, the mechanism forces poisoning attempts to manifest as deterministic reconstruction residuals, thereby exposing structure-violating output and rule poisoning attacks. Theoretical analysis confirms that PEEL, as a post-randomization encoding layer, preserves the unbiasedness and statistical accuracy of the underlying LDP protocols, while deterministically exposing structure-violating output and rule poisoning attacks. Extensive evaluations across six protocols and two real-world datasets confirm that PEEL reduces client-side overheads by orders of magnitude compared to cryptographic baselines, while maintaining F1 scores exceeding 99.8% against structure-violating output and rule poisoning attacks.
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 4777-4794
Open AccessPEEL: A Poisoning-Exposing Encoding Mechanism for Local Differential Privacy
Local Differential Privacy (LDP) has emerged as a dominant privacy paradigm in the Internet of Things (IoT) due to its lightweight, decentralized and scalable nature. However, the indistinguishability guarantee inherent to LDP mechanisms inadvertently masks adversarial manipulation, rendering poisoned data difficult to differentiate from legitimate perturbations. Existing poisoning defense mechanisms either incur prohibitive overheads incompatible with resource-constrained IoT devices or rely on rigid domain priors. To address this, we propose PEEL, a Poisoning-Exposing Encoding mechanism for LDP, which reformulates poisoning exposure as a geometric structural verification problem within the encoding subspace. Departing from probabilistic statistical filtering, PEEL exploits the rank disparity between legitimate sparse perturbations and arbitrary adversarial injections. By projecting LDP outputs onto a low-rank structural support, the mechanism forces poisoning attempts to manifest as deterministic reconstruction residuals, thereby exposing structure-violating output and rule poisoning attacks. Theoretical analysis confirms that PEEL, as a post-randomization encoding layer, preserves the unbiasedness and statistical accuracy of the underlying LDP protocols, while deterministically exposing structure-violating output and rule poisoning attacks. Extensive evaluations across six protocols and two real-world datasets confirm that PEEL reduces client-side overheads by orders of magnitude compared to cryptographic baselines, while maintaining F1 scores exceeding 99.8% against structure-violating output and rule poisoning attacks.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (19) , 39991-40007
PoisonCatcher: Revealing and Identifying LDP Poisoning Attacks in IIoT
Local differential privacy (LDP), a robust privacy-protection model, is widely adopted in the Industrial Internet of Things (IIoT) due to its lightweight, decentralized, and scalable. However, its perturbation-based privacy-protection mechanism hinders distinguishing between any two data, thereby facilitating LDP poisoning attacks. The exposed physical-layer vulnerabilities and resource-constrained prevalent at the IIoT edge not only facilitate such attacks but also render existing LDP poisoning defenses, all of which are deployed at the edge and rely on ample resources, impractical. This work proposes a LDP poisoning defense for IIoT in the resource-rich aggregator. We first reveal key poisoning attack modes occurring within the LDP-utilized IIoT data-collection process, detailing how IIoT vulnerabilities enable attacks, and then formulate a general attack model and derive the poisoned data’s indistinguishability. This work subsequently analyzes the poisoning impacts on aggregated data based on industrial process correlation, revealing the distortion of statistical query result’ temporal similarity and the resulting disruption of interattribute correlation, and uncovering the intriguing paradox that adversaries’ attempts to stabilize their poisoning actions for stealth are difficult to maintain. Given these findings, we propose PoisonCatcher, a solution for identifying poisoned data, which includes time-series detectors based on temporal similarity, attribute correlation, and pattern stability metrics to detect poisoned attributes, and a latent-bias feature miner for identifying poisons. Experiments on two representative real-world datasets indicate that PoisonCatcher successfully identifies poisoned data, demonstrating robust identification capabilities with F2 scores above 90.7% under various attack settings.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (19) , 39991-40007
PoisonCatcher: Revealing and Identifying LDP Poisoning Attacks in IIoT
Local differential privacy (LDP), a robust privacy-protection model, is widely adopted in the Industrial Internet of Things (IIoT) due to its lightweight, decentralized, and scalable. However, its perturbation-based privacy-protection mechanism hinders distinguishing between any two data, thereby facilitating LDP poisoning attacks. The exposed physical-layer vulnerabilities and resource-constrained prevalent at the IIoT edge not only facilitate such attacks but also render existing LDP poisoning defenses, all of which are deployed at the edge and rely on ample resources, impractical. This work proposes a LDP poisoning defense for IIoT in the resource-rich aggregator. We first reveal key poisoning attack modes occurring within the LDP-utilized IIoT data-collection process, detailing how IIoT vulnerabilities enable attacks, and then formulate a general attack model and derive the poisoned data’s indistinguishability. This work subsequently analyzes the poisoning impacts on aggregated data based on industrial process correlation, revealing the distortion of statistical query result’ temporal similarity and the resulting disruption of interattribute correlation, and uncovering the intriguing paradox that adversaries’ attempts to stabilize their poisoning actions for stealth are difficult to maintain. Given these findings, we propose PoisonCatcher, a solution for identifying poisoned data, which includes time-series detectors based on temporal similarity, attribute correlation, and pattern stability metrics to detect poisoned attributes, and a latent-bias feature miner for identifying poisons. Experiments on two representative real-world datasets indicate that PoisonCatcher successfully identifies poisoned data, demonstrating robust identification capabilities with F2 scores above 90.7% under various attack settings.