← Search

Geyuan Zhang

2 accepted papers

2026

AICrypto: Evaluating Cryptography Capabilities of Large Language Models

ICML 2026poster

Large language models (LLMs) have demonstrated remarkable capabilities across a variety of domains. However, their applications in cryptography, which serve as a foundational pillar of cybersecurity, remain largely unexplored. To address this gap, we build \textbf{AICrypto}, a comprehensive benchmar…

Cited by 0SourceScholar
2025

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

ACL 2025long

With the rapid advancement of Large Vision-Language Models (VLMs), concerns about their ‌potential misuse and abuse have grown rapidly. Prior research has exposed VLMs’ vulnerability to jailbreak attacks, where carefully crafted inputs can lead the model to produce content that violates ethical and…