Search papers, labs, and topics across Lattice.
School of Artificial Intelligence, Beihang University
4
0
6
4
FedSEPT achieves superior local adaptation without sacrificing global generalization, even under stringent privacy conditions.
Hallucinated outputs trigger unique gradient patterns in LLMs, enabling AURORA to achieve superior detection performance across diverse tasks and models.
By intelligently perturbing class prototypes based on their discriminative power, VPDR achieves a superior privacy-utility trade-off in federated learning compared to naive Gaussian noise.
Forget likelihood scores and fine-tuning tricks: LLMs leak pre-training data membership through subtle, yet detectable, deviations in their gradient updates.
