Robustness of Retrieval-Augmented Vulnerability Classifiers Under Adversarial Inputs

Abstract

Abstract: This report synthesises findings from 10 peer-reviewed papers addressing the following research question: How does the robustness of vulnerability classification models like Gemini 1.5 Pro and Llama3-70B with retrieval augmentation vary when presented with adversarial or noisy inputs in the CodeXGLUE. We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks. We provide. 16 claims were extracted from source literature; 15 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the robustness of vulnerability classification models like Gemini 1.5 Pro and Llama3-70B with retrieval augmentation vary when presented with adversarial or noisy inputs in the CodeXGLUE security subset, measured in accuracy degradation or robustness metrics?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance