Saerom Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Saerom Park has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Jaewook Lee
Seoul National University
5 shared publications Jaewook Lee
Industrial Engineering, Seoul National University, 1 Gwanakro, Gwanak-gu, Seoul, 08826, Republic of Korea
3 shared publications- Junyoung Byun
Department of Applied Statistics, Chung-Ang University, Seoul, Republic of Korea
3 shared publications - Yujin Choi
Seoul National University
3 shared publications - Hojin Lee
UNIST, Ulsan, Republic of Korea
2 shared publications - Jieun Yun
Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5976-5986
LogoGate: Object-Aware Logo-Exposure Backdoor Attack for Text-to-Image Models
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5976-5986
Open AccessLogoGate: Object-Aware Logo-Exposure Backdoor Attack for Text-to-Image Models
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2391-2401
Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Data
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2391-2401
Open AccessSeq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Data
- Open Access
- 26 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13-17
MER-SoLa: Confusion-based Soft Labeling for Multimodal Emotion Recognition
- 26 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13-17
Open AccessMER-SoLa: Confusion-based Soft Labeling for Multimodal Emotion Recognition
- 3 September 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (10) , 1-17
HACOE: hierarchical attack classification with outlier exposure
- 3 September 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (10) , 1-17
HACOE: hierarchical attack classification with outlier exposure
- 14 June 2025
- Published by Springer Nature
- p. 111-137
Efficient Privacy-Preserving Counting Method with Homomorphic Encryption
- 14 June 2025
- Published by Springer Nature
- p. 111-137
Efficient Privacy-Preserving Counting Method with Homomorphic Encryption
- 26 November 2024
- Published by Springer Nature in International Journal of Information Security
- Vol. 24 (1) , 1-15
Verifiable computation over encrypted data via MPC-in-the-head zero-knowledge proofs
- 26 November 2024
- Published by Springer Nature in International Journal of Information Security
- Vol. 24 (1) , 1-15
Verifiable computation over encrypted data via MPC-in-the-head zero-knowledge proofs
- 26 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 256
Privacy-preserving inference resistant to model extraction attacks
- 26 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 256
Privacy-preserving inference resistant to model extraction attacks
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (20) , 21995-22003
Fair Sampling in Diffusion Models through Switching Mechanism
Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms of fairness. While the sampling process of diffusion models can be controlled by conditional guidance, previous works have attempted to find empirical guidance to achieve quantitative fairness. To address this limitation, we propose a fairness-aware sampling method called \textit{attribute switching} mechanism for diffusion models. Without additional training, the proposed sampling can obfuscate sensitive attributes in generated data without relying on classifiers. We mathematically prove and experimentally demonstrate the effectiveness of the proposed method on two key aspects: (i) the generation of fair data and (ii) the preservation of the utility of the generated data.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (20) , 21995-22003
Open AccessFair Sampling in Diffusion Models through Switching Mechanism
Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms of fairness. While the sampling process of diffusion models can be controlled by conditional guidance, previous works have attempted to find empirical guidance to achieve quantitative fairness. To address this limitation, we propose a fairness-aware sampling method called \textit{attribute switching} mechanism for diffusion models. Without additional training, the proposed sampling can obfuscate sensitive attributes in generated data without relying on classifiers. We mathematically prove and experimentally demonstrate the effectiveness of the proposed method on two key aspects: (i) the generation of fair data and (ii) the preservation of the utility of the generated data.
- 15 August 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (9) , 10114-10129
Efficient homomorphic encryption framework for privacy-preserving regression
- 15 August 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (9) , 10114-10129
Efficient homomorphic encryption framework for privacy-preserving regression
- Open Access
- 8 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 61707-61720
Efficient Generation of Program Execution Hash
Distributed computing systems often require verifiable computing techniques in case their node is untrusted. To verify a node’s computation result, proof-of-work (PoW) is often utilized as a basis of verifiable computing method; however, this mechanism is only valid for computations producing results based on specific algorithm (e.g., AES decryption). To date, there is no efficient PoW mechanism applicable to arbitrary algorithm or a computation that does not produce any tangible output (e.g., void function). This paper proposes execution hash to serve as a proof for a program’s idempotent computation result without relying on its algorithm. Two versions of execution hash generation methods were designed and implemented and the efficacy was evaluated in terms of performance and reliability. Implementation was based on LLVM/Clang 6.0 and evaluation was based on open-source software, including GNU binutils/coreutils and Google’s OSSFuzz projects.
- 8 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 61707-61720
Open AccessEfficient Generation of Program Execution Hash
Distributed computing systems often require verifiable computing techniques in case their node is untrusted. To verify a node’s computation result, proof-of-work (PoW) is often utilized as a basis of verifiable computing method; however, this mechanism is only valid for computations producing results based on specific algorithm (e.g., AES decryption). To date, there is no efficient PoW mechanism applicable to arbitrary algorithm or a computation that does not produce any tangible output (e.g., void function). This paper proposes execution hash to serve as a proof for a program’s idempotent computation result without relying on its algorithm. Two versions of execution hash generation methods were designed and implemented and the efficacy was evaluated in terms of performance and reliability. Implementation was based on LLVM/Clang 6.0 and evaluation was based on open-source software, including GNU binutils/coreutils and Google’s OSSFuzz projects.