7 papers
KeyPooling: Measuring Where LLM API Relay Paths Collapse Prompt Cache Isolation
Bowen Sun, Yixi Cai, Xiaogeng Liu +3
Large language model (LLM) API relays authenticate customers separately but often forward requests through shared provider credentials. Providers scope prompt caches to upstream pr…
A Robust Certified Machine Unlearning Method Under Distribution Shift
Jinduo Guo, Yinzhi Cao
The Newton method has been widely adopted to achieve certified unlearning. A critical assumption in existing approaches is that the data requested for unlearning are selected i.i.d…
PILOT: Command-line Interface Fuzzing via Path-Guided, Iterative Large Language Model Prompting
Momoko Shiraishi, Yinzhi Cao, Takahiro Shinagawa
Command-line interface (CLI) fuzzing tests programs by mutating both command-line options and input file contents, thus enabling discovery of vulnerabilities that only manifest und…
Mirror Mirror on the Wall, Have I Forgotten it All? A New Framework for Evaluating Machine Unlearning
Brennon Brimhall, Philip Mathew, Neil Fendley +2
Machine unlearning methods take a model trained on a dataset and a forget set, then attempt to produce a model as if it had only been trained on the examples not in the forget set.…
SmartC2Rust: Iterative, Feedback-Driven C-to-Rust Translation via Large Language Models for Safety and Equivalence
Momoko Shiraishi, Yinzhi Cao, Takahiro Shinagawa
Memory safety vulnerabilities remain prevalent in today's software systems and one promising solution to mitigate them is to adopt memory-safe languages such as Rust. Due to legacy…
AuthNet: Neural Network with Integrated Authentication Logic
Yuling Cai, Fan Xiang, Guozhu Meng +2
Model stealing, i.e., unauthorized access and exfiltration of deep learning models, has become one of the major threats. Proprietary models may be protected by access controls and…