local differential privacy 1poisoning attacks 1randomized projection 1robust statistics 1sparse vector estimation 1
From the 1 of 3 linked papers with an AI index.
3 papers
stat.ML2026
Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy
Puning Zhao, Zhikun Zhang, Shaowei Wang +5
The paper proposes a Randomized Projection with Clipping (RPC) method to robustly estimate sparse numerical vectors under local differential privacy, providing theoretical error gu…
cs.LG2026
Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
Mengnan Zhao, Lihe Zhang, Tianhang Zheng +2
Fast Adversarial Training (FAT) has attracted significant attention due to its efficiency in enhancing neural network robustness against adversarial attacks. However, FAT is prone…
cs.LG2026
Mitigating Error Amplification in Fast Adversarial Training
Mengnan Zhao, Lihe Zhang, Bo Wang +3
Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representations. However, FAT often suffe…