Zelong Zhang

Attacking High-order Masked Cryptosystem via Deep Learning-based Side-Channel Analysis

2024

Masking is widely considered as an effective countermeasure against side-channel analysis (SCA) due to its provable security and efficiency. However, recent works have demonstrated that the deep learning-based SCA (DL-SCA) can effectively break the cryptographic …

Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions

2025 · arXiv (Cornell University)

Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative interactions. However, existing …