zknews

trending1

01▲
Unsaid, Unsafe? Implicit Security Obligations in LLM-Based RTL Code Generation arxiv.org
Can an LLM emit functionally correct RTL that still leaks? This paper says yes, and adds SECRTL-GEN plus RTL-Obliger.
arxiv benchmark cwe hardware-security llm rtl secure-generation symbolic-ai systemverilog verilog vhdl
0 pts/viktor/14 days ago/2 comments