arXiv AI
Interpreting and Steering for Safe and Correct Code Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 25
Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning
The paper introduces CodeScan, a black-box, vulnerability-oriented scanning framework designed to detect data poisoning and backdoor attacks in code generation large language models (LLMs). CodeScan operates by analyzing structural similarities across multiple code generations, normalizing them with abstract syntax tree (AST) techniques, and then applying LLM-based vulnerability analysis to identify recurring insecure patterns. Evaluations on 117 models across three architectures and multiple sizes show over 97% detection accuracy with fewer false positives compared to prior methods.
arXiv AI
Jul 3
Safety Targeted Embedding Exploit via Refinement
arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.
arXiv AI
Oct 21
When Models Know but Can't Linearly Say: Relational Encoding Limits Linear Vulnerability Classification in Code LLMs
arXiv:2610.27257v1 Announce Type: cross Abstract: Large language models can detect vulnerable code, yet the form of vulnerability encoding in their representations remains unclear. We analyze 8 code...
arXiv AI
Jun 16
DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents
arXiv:2511. 20709v2 Announce Type: replace-cross Abstract: Large language models (LLMs) and LLM-based coding agents are now used to generate code from natural-language specifications, yet ensuring such code is both functionally correct and secure remains a challenge.
arXiv AI
Oct 1
CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion
arXiv:2609.39902v1 Announce Type: cross Abstract: Large language models have achieved remarkable capabilities across diverse domains, yet their safety alignment remains vulnerable to jailbreak attack...
Hugging Face Trending Papers
Jul 2
Safety Targeted Embedding Exploit via Refinement
Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.