Michael R. Lyu
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2Software Eng.×1AI×1
Frequent co-authors
Research Timeline
2026
Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective
This paper investigates how Byte-Pair Encoding (BPE) tokenization causes Code LLMs to disproportionately memorize certain types of secrets, a phenomenon termed 'gibberish bias'.
VulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair Patterns
VulKey introduces a novel LLM-based framework that uses a hierarchical abstraction of expert security knowledge to guide automatic vulnerability repair, achieving state-of-the-art performance on real-world benchmarks.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.SERecentMay 3, 2026
VulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair Patterns
VulKey introduces a novel LLM-based framework that uses a hierarchical abstraction of expert security knowledge to guide automatic vulnerability repair, achieving state-of-the-art performance on real-…
View →
cs.CRcs.AIRecentApr 20, 2026