Yushun Dong

With over 216,000 skills sourced from both academic and community contributions, SkillCenter transforms the landscape of operational knowledge for autonomous AI agents.

AGDN not only solves the Traveling Salesman Problem more effectively but also maintains optimal connectivity in solutions that traditional methods often overlook.

Attackers waste their query budgets on trivial knowledge while legitimate users enjoy uninterrupted access, thanks to the Knowledge Trap.

Publicly available data can significantly inform wildfire initial attack failure predictions, but it only captures part of the picture.

An embarrassingly simple yet highly effective detector achieves 100% true positive rates for model extraction attacks while maintaining an exceptionally low false positive rate.

Latent reasoning can now be validated in real-time, with a novel method that boosts accuracy by over 16 points on critical benchmarks.

LLMs can prune noisy edges in EEG graphs, leading to more accurate and interpretable seizure detection.

By explicitly accounting for EEG's noisy nature, IRENE learns compact and reliable connectivity patterns that boost seizure detection performance beyond SOTA methods.

Finally, a defense against model extraction comes with rigorous theoretical guarantees, using mutual information to certify DNN ownership.

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.

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.