Zachary Coalson

11 papers A* 1A 1Journal 9

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs. CoRR Zachary Coalson, Bo Fang, Sanghyun Hong
2026	J	`jnl`	Discovering Universal Activation Directions for PII Leakage in Language Models. CoRR Leo Marchyok, Zachary Coalson, Sungho Keum, Sooel Son, Sanghyun Hong
2026	J	`jnl`	Fail-Closed Alignment for Large Language Models. CoRR Zachary Coalson, Beth Sohler, Aiden Gabriel, Sanghyun Hong
2025	A	`conf`	Demystifying the Resilience of Large Language Model Inference: An End-to-End Perspective. SC Yu Sun, Zachary Coalson, Shiyang Chen, Hang Liu, Zhao Zhang, Sanghyun Hong, Bo Fang, Lishan Yang
2025	J	`jnl`	Hard Work Does Not Always Pay Off: On the Robustness of NAS to Data Poisoning. Trans. Mach. Learn. Res. Zachary Coalson, Huazheng Wang, Qingyun Wu, Sanghyun Hong
2025	J	`jnl`	Harnessing Input-Adaptive Inference for Efficient VLN. CoRR Dongwoo Kang, Akhil Perincherry, Zachary Coalson, Aiden Gabriel, Stefan Lee, Sanghyun Hong
2025	J	`jnl`	IF-GUIDE: Influence Function-Guided Detoxification of LLMs. CoRR Zachary Coalson, Juhan Bae, Nicholas Carlini, Sanghyun Hong
2024	J	`jnl`	Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search. CoRR Zachary Coalson, Huazheng Wang, Qingyun Wu, Sanghyun Hong
2024	J	`jnl`	PrisonBreak: Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips. CoRR Zachary Coalson, Jeonghyun Woo, Shiyang Chen, Yu Sun, Lishan Yang, Prashant J. Nair, Bo Fang, Sanghyun Hong
2023	A*	`conf`	BERT Lost Patience Won't Be Robust to Adversarial Slowdown. NeurIPS Zachary Coalson, Gabriel Ritter, Rakesh Bobba, Sanghyun Hong
2023	J	`jnl`	BERT Lost Patience Won't Be Robust to Adversarial Slowdown. CoRR Zachary Coalson, Gabriel Ritter, Rakesh Bobba, Sanghyun Hong

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.

In 2025, he co-authored Assessing the Effectiveness of the Tigress Obfuscator Against MOPSA and BinaryNinja, published at CheckMATE. The paper evaluates the effectiveness of obfuscation techniques and their impact on source-level static analysis and binary-level decompilation.

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.