6 papers
Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding
Adam Å torek, Mukur Gupta, Samira Hajizadeh +2
Large language models (LLMs) are increasingly deployed for understanding large codebases, but whether they understand operational semantics of long code context or rely on pattern…
TIF: Learning Temporal Invariance in Android Malware Detectors
Xinran Zheng, Shuo Yang, Edith C. H. Ngai +2
Learning-based Android malware detectors degrade over time due to natural distribution drift caused by malware variants and new families. This paper systematically investigates the…
XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants
Adam Å torek, Mukur Gupta, Noopur Bhatt +4
AI coding assistants are widely used for tasks like code generation. These tools now require large and complex contexts, automatically sourced from various origins$\unicode{x2014}$…
NanoTag: Systems Support for Efficient Byte-Granular Overflow Detection on ARM MTE
Mingkai Li, Hang Ye, Joseph Devietti +2
Memory safety bugs, such as buffer overflows and use-after-frees, are the leading causes of software safety issues in production. Software-based approaches, e.g., Address Sanitizer…
Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models
Xinran Zheng, Xingzhi Qian, Huichi Zhou +4
Language models (LMs) show promise for vulnerability detection but struggle with long, real-world code due to sparse and uncertain vulnerability locations. These issues, exacerbate…
CodeSCM: Causal Analysis for Multi-Modal Code Generation
Mukur Gupta, Noopur Bhatt, Suman Jana
In this paper, we propose CodeSCM, a Structural Causal Model (SCM) for analyzing multi-modal code generation using large language models (LLMs). By applying interventions to CodeSC…