Zhengyang Shan
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2AI×1
Frequent co-authors
Research Timeline
2026
SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection
The paper proposes SAGE, a framework that uses Signal-Amplified Guided Embeddings to overcome 'Signal Submersion' in LLMs, significantly boosting vulnerability detection accuracy across multiple programming languages.
ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
The paper introduces ASPI, a benchmark showing that requiring LLM agents to seek clarification significantly amplifies their vulnerability to prompt injection attacks.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIRecentMay 17, 2026
ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
The paper introduces ASPI, a benchmark showing that requiring LLM agents to seek clarification significantly amplifies their vulnerability to prompt injection attacks.
View →
cs.CRRecentApr 21, 2026