Search papers, labs, and topics across Lattice.
Florida State University
5
0
7
0
By explicitly accounting for EEG's noisy nature, IRENE learns compact and reliable connectivity patterns that boost seizure detection performance beyond SOTA methods.
Stop model extraction attacks on your GNNs without sacrificing accuracy: CITED uses a novel decision boundary signature to prove ownership at both the embedding and label levels.
Finally, a defense against model extraction comes with rigorous theoretical guarantees, using mutual information to certify DNN ownership.
Suppressing non-stationary frequencies in time series data yields surprisingly large gains in forecasting accuracy and computational efficiency.
A unified benchmark reveals the fragmented landscape of RAG security, highlighting vulnerabilities to knowledge-extraction attacks and paving the way for robust defense strategies.
