Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
On the second-order optimization for spiking neural networks
Ngoc Phu Doan, Ihsen Alouani
Spiking Neural Networks (SNNs) offer an energy-efficient alternative to conventional neural networks by exploiting sparse, binary spikes, and event-driven computation. However, the…
cs.LG2026
Batch Normalization Amplifies Memorization and Privacy Risks
Ngoc Phu Doan, Chongyan Gu, Ihsen Alouani
Batch Normalization (BN) is widely adopted to enable faster convergence and more stable training of deep neural networks. However, its impact on privacy and memorization has remain…
cs.LG2026
AttenMIA: LLM Membership Inference Attack through Attention Signals
Pedram Zaree, Md Abdullah Al Mamun, Yue Dong +2
Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency…