Large models support great zero-shot and few-shot capabilities. However,...
The advent of personalized reality has arrived. Rapid development in AR/...
Adapting model parameters to incoming streams of data is a crucial facto...
Inspired by recent work on neural subspaces and mode connectivity, we re...
While different methods exist to tackle distinct types of distribution s...
Desktop browser extensions have long allowed users to improve their
expe...
Digital harms can manifest across any interface. Key problems in address...
Recent exploration of the multi-agent backdoor attack demonstrated the
b...
Malicious agents in collaborative learning and outsourced data collectio...
Attack vectors that compromise machine learning pipelines in the physica...
Digital harms are widespread in the mobile ecosystem. As these devices g...
As collaborative learning and the outsourcing of data collection become ...
Dark patterns in mobile apps take advantage of cognitive biases of end-u...
The paper explores a novel methodology in source code obfuscation throug...