3 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.
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...
BASIS, a critic-free post-training algorithm designed to address the tradeoff between computational efficiency and sample efficiency in value estimation and policy learning, achieves performance close to multi-rollout GRPO-type baselines and often outperforms single-rollout REINFORCE-type baselines.
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...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
