SVAgent: AI Agent for Hardware Security Verification Assertion
This addresses verification bottlenecks for hardware security engineers in integrated circuit design, though it appears incremental as an enhancement to existing automation frameworks.
The paper tackles the inefficiency and limitations of manual SystemVerilog assertion (SVA) development for detecting hardware security vulnerabilities by proposing SVAgent, an automatic SVA generation framework that improves accuracy and consistency over existing methods and integrates into mainstream vulnerability assessment tools.
Verification using SystemVerilog assertions (SVA) is one of the most popular methods for detecting circuit design vulnerabilities. However, with the globalization of integrated circuit design and the continuous upgrading of security requirements, the SVA development model has exposed major limitations. It is not only inefficient in development, but also unable to effectively deal with the increasing number of security vulnerabilities in modern complex integrated circuits. In response to these challenges, this paper proposes an innovative SVA automatic generation framework SVAgent. SVAgent introduces a requirement decomposition mechanism to transform the original complex requirements into a structured, gradually solvable fine-grained problem-solving chain. Experiments have shown that SVAgent can effectively suppress the influence of hallucinations and random answers, and the key evaluation indicators such as the accuracy and consistency of the SVA are significantly better than existing frameworks. More importantly, we successfully integrated SVAgent into the most mainstream integrated circuit vulnerability assessment framework and verified its practicality and reliability in a real engineering design environment.