Author

Stephen J. Roberts

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Hidden in the Comments: A Context-Injection Attack Surface in Code LLMs

Code large language model (Code LLM) assistants generate code from heterogeneous development contexts, including open files, imported modules, pasted snippets, and comments, much of which may originate from untrusted sources. We investigate whether insecure instructions embedded in such contexts can steer Code LLMs tow...

Noor Munir, Francesco Quinzan, Stephen J. Roberts · 0 citations

Preprint Aug 2026

Detecting Contaminated Code-Generation Prompt Batches via Influence Functions

The proposed CodeSIFT, a threat-model-agnostic detection method that leverages influence functions to identify batches of prompts that induce anomalous model behavior, suggests that influence-function-based detection is a promising direction for identifying malicious code-generation prompts without requiring prior know...

Francesco Quinzan, Noor Munir, Yi-Shun Lu et al. · 1 citation