Takayuki Miura

27 papers A* 1B 1C 1Journal 14Unranked 10

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Active Synthetic Data Generation with Joint Consideration of Differential Privacy and Labeling Efficiency. J. Inf. Process. Osamu Saisho, Takayuki Miura, Kazuki Iwahana, Masanobu Kii, Rina Okada
2025	J	`jnl`	Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets. CoRR Tomoya Yamashita, Yuuki Yamanaka, Masanori Yamada, Takayuki Miura, Toshiki Shibahara, Tomoharu Iwata
2025	—	`conf`	Efficient Privacy-Preserving Data Annotation via Active PrivBayes Synthetic Data Generation. PerCom Workshops Osamu Saisho, Takayuki Miura, Kazuki Iwahana, Masanobu Kii, Rina Okada
2025	—	`conf`	Enhancing Jailbreak Resistance in Large Language Models Using Model Merge. SP (Workshops) Saki Hiromi, Hiroki Kinoshita, Masanori Yamada, Takayuki Miura
2025	—	`conf`	Explaining and Visualizing Synthetic Data Quality Using Statistical Distances. EuroS&P (Workshops) Juko Yamamoto, Takayuki Miura, Rina Okada, Masanobu Kii, Atsunori Ichikawa
2025	J	`jnl`	Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial? CoRR Akira Ito, Takayuki Miura, Yosuke Todo
2025	J	`jnl`	Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial? IACR Cryptol. ePrint Arch. Akira Ito, Takayuki Miura, Yosuke Todo
2025	J	`jnl`	Lightweight Two-Party Secure Sampling Protocol for Differential Privacy. Proc. Priv. Enhancing Technol. Masanobu Kii, Atsunori Ichikawa, Takayuki Miura
2025	—	`conf`	Membership Inference Attack Against Bayesian Neural Network. ICC Toshiki Shibahara, Takayuki Miura, Masanobu Kii, Atsunori Ichikawa
2025	A*	`conf`	Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference. ICML Yusuke Yamasaki, Kenta Niwa, Daiki Chijiwa, Takumi Fukami, Takayuki Miura
2025	J	`jnl`	Quo Vadis Diffusion Model? A Case for Membership Inference Attacks. IEICE Trans. Inf. Syst. Tomoya Matsumoto, Takayuki Miura, Shingo Okamura, Behrouz Zolfaghari, Naoto Yanai
2025	J	`jnl`	Robust Backdoor Removal by Reconstructing Trigger-Activated Changes in Latent Representation. CoRR Kazuki Iwahana, Yusuke Yamasaki, Akira Ito, Takayuki Miura, Toshiki Shibahara
2025	J	`jnl`	Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models. CoRR Tomoya Yamashita, Akira Ito, Yuuki Yamanaka, Masanori Yamada, Takayuki Miura, Toshiki Shibahara
2024	B	`conf`	Efficiently Calculating Stronger Lower Bound for Differentially Private SGD in Black-Box Setting. COMPSAC Toshiki Shibahara, Takayuki Miura, Masanobu Kii, Atsunori Ichikawa
2024	—	`conf`	Evaluating Synthetic Data Generation Techniques for Medical Dataset. BIOSTEC (2) Takayuki Miura, Eizen Kimura, Atsunori Ichikawa, Masanobu Kii, Juko Yamamoto
2024	—	`conf`	Leveraging Timestamps to Create Secure and Feeless Evidence Management. Blockchain Iifan Tyou, Shigenori Ohashi, Justin Yu, Takayuki Miura, Takuro Hosoi, Kanta Matsuura
2024	—	`conf`	MEGEX: Data-Free Model Extraction Attack Against Gradient-Based Explainable AI. SecTL@AsiaCCS Takayuki Miura, Toshiki Shibahara, Naoto Yanai
2024	J	`jnl`	REN-A.I.: A Video Game for AI Security Education Leveraging Episodic Memory. IEEE Access Mine Arai, Koki Tejima, Yuya Yamada, Takayuki Miura, Kyosuke Yamashita, Chihiro Kado, Rei Shimizu, Masataka Tatsumi, Naoto Yanai, Goichiro Hanaoka
2024	J	`jnl`	SETSUBUN: Revisiting Membership Inference Game for Evaluating Synthetic Data Generation. J. Inf. Process. Takayuki Miura, Masanobu Kii, Toshiki Shibahara, Kazuki Iwahana, Tetsuya Okuda, Atsunori Ichikawa, Naoto Yanai
2023	—	`conf`	Can Inputs' Reconstruction Information Be Coded into Machine Learning Model's Outputs? ESORICS Workshops (2) Kazuki Iwahana, Osamu Saisho, Takayuki Miura, Akira Ito
2023	—	`conf`	Membership Inference Attacks against Diffusion Models. SP (Workshops) Tomoya Matsumoto, Takayuki Miura, Naoto Yanai
2023	J	`jnl`	Membership Inference Attacks against Diffusion Models. CoRR Tomoya Matsumoto, Takayuki Miura, Naoto Yanai
2023	J	`jnl`	On Rényi Differential Privacy in Statistics-Based Synthetic Data Generation. CoRR Takayuki Miura, Toshiki Shibahara, Masanobu Kii, Atsunori Ichikawa, Juko Yamamoto, Koji Chida
2023	J	`jnl`	On Rényi Differential Privacy in Statistics-based Synthetic Data Generation. J. Inf. Process. Takayuki Miura, Toshiki Shibahara, Masanobu Kii, Atsunori Ichikawa, Juko Yamamoto, Koji Chida
2021	J	`jnl`	MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AI. CoRR Takayuki Miura, Satoshi Hasegawa, Toshiki Shibahara
2020	C	`conf`	Differential Privacy and Its Applicability for Official Statistics in Japan - A Comparative Study Using Small Area Data from the Japanese Population Census. PSD Shinsuke Ito, Takayuki Miura, Hiroto Akatsuka, Masayuki Terada
2016	—	`conf`	Designing Affordances for Virtual Reality-Based Services with Natural User Interaction. HCI (18) Takayuki Miura, Akihito Yoshii, Tatsuo Nakajima

Nicolò Altamura is a security engineer and computer science researcher specializing in software protection, reverse engineering, program analysis, and binary deobfuscation. He holds a master's degree in Computer Science and Engineering from the University of Verona, graduating with honors, and works at emproof, focusing on software protection and the challenges of analyzing and understanding compiled software.

His research explores the relationship between program analysis and code obfuscation, with particular emphasis on how software transformations affect the ability of automated tools to recover program behavior. His interests span static analysis, binary analysis, decompilation, reverse engineering, and techniques for analyzing and simplifying obfuscated code.

Beyond academic research, Nicolò develops and contributes to tools for reverse engineering and software analysis. His projects include obfuscation_analysis, a Binary Ninja plugin for analyzing and simplifying obfuscated code; Pocket, an obfuscator for mixed Boolean-arithmetic expressions; and ptxNinja, a tool for reverse engineering NVIDIA GPU code represented in the PTX virtual instruction set.

His research also extends to binary datasets and software evolution. In 2026, he co-authored ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage, a research work addressing the availability of binary data across multiple software builds and points in time, supporting research into binary analysis and changes between program versions.

Across his research, engineering work, and open-source contributions, Nicolò focuses on advancing the understanding, analysis, and protection of software against increasingly sophisticated obfuscation and reverse-engineering challenges.

Nicolò Altamura is not a football player. Please avoid reporting this kind of infromation.