4 papers
A Systematic Methodology for Evaluating Failure Independence in LLM-Generated Code
Rodrigo Pato Nogueira, Karthik Pattabiraman, Marco Vieira +1
N-Version Programming (NVP) improves software reliability by executing multiple independent implementations and combining outputs, but its adoption is limited by high cost and the…
AIReSim: A Discrete Event Simulator for Large-scale AI Cluster Reliability Modeling
Karthik Pattabiraman, Mihir Patel, Fred Lin
Failures in clusters running large-scale AI workloads can result in decreased utilization. Because the cost of a failure in such AI workloads is high (as it requires restarting the…
RVDebloater: Mode-based Adaptive Firmware Debloating for Robotic Vehicles
Mohsen Salehi, Karthik Pattabiraman
As the number of embedded devices grows and their functional requirements increase, embedded firmware is becoming increasingly larger, thereby expanding its attack surface. Despite…
Anonymity Unveiled: A Practical Framework for Auditing Data Use in Deep Learning Models
Zitao Chen, Karthik Pattabiraman
The rise of deep learning (DL) has led to a surging demand for training data, which incentivizes the creators of DL models to trawl through the Internet for training materials. Mea…