Robustness of Domain-Adapted LLaVul Models vs. Fine-Tuned SLMs Against Adversarial Code Perturbations

This report synthesises findings from 1 peer-reviewed paper addressing the following research question: How robust are domain-adapted LLaVul models compared to fine-tuned SLMs against adversarial perturbations in code, as measured by accuracy degradation on the CWE-78 and CWE-476 benchmarks when. Deep learning approaches to anomaly detection (AD) have recently improved the state of the art in detection performance on complex data sets, such as large collections of images or text. These results have sparked a renewed interest in the AD problem and led to the introduction. 11 claims were extracted from source literature; 10 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.1/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How robust are domain-adapted LLaVul models compared to fine-tuned SLMs against adversarial perturbations in code, as measured by accuracy degradation on the CWE-78 and CWE-476 benchmarks when subjected to syntactic or semantic obfuscation?

Autonomous literature synthesis. Automated review score: 8.1/10. Full text and citation available at Assignee Research.