6 papers
GIF: Locally Sound Geometric Information Flow Control for LLMs
Adam Storek, Nikolaus Holzer, Zhuo Zhang +1
Large language models increasingly mediate interactions between sensitive data, untrusted inputs, and privileged actions in agentic systems, creating security and privacy risks. Th…
Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks
Adam Štorek, Vikas Upadhyay, Marianne Menglin Liu +6
LLMs now tackle a wide range of software-related tasks, yet we show that their performance varies markedly both across and within these tasks. Routing user queries to the appropria…
Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding
Adam Štorek, 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…
XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants
Adam Štorek, 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$\unicode{x2014}$…
FOX: Coverage-guided Fuzzing as Online Stochastic Control
Dongdong She, Adam Storek, Yuchong Xie +3
Fuzzing is an effective technique for discovering software vulnerabilities by generating random test inputs and executing them against the target program. However, fuzzing large an…
Unsupervised Selective Rationalization with Noise Injection
Adam Storek, Melanie Subbiah, Kathleen McKeown
A major issue with using deep learning models in sensitive applications is that they provide no explanation for their output. To address this problem, unsupervised selective ration…