no code implementations • 2 May 2024 • Yipeng Li, Xinchen Lyu
There are two paradigms in Federated Learning (FL): parallel FL (PFL), where models are trained in a parallel manner across clients; and sequential FL (SFL), where models are trained in a sequential manner across clients.
no code implementations • 24 Jan 2024 • Junlin Liu, Xinchen Lyu
Adversarial examples are one critical security threat to various visual applications, where injected human-imperceptible perturbations can confuse the output. Generating transferable adversarial examples in the black-box setting is crucial but challenging in practice.
2 code implementations • NeurIPS 2023 • Yipeng Li, Xinchen Lyu
There are two categories of methods in Federated Learning (FL) for joint training across multiple clients: i) parallel FL (PFL), where clients train models in a parallel manner; and ii) sequential FL (SFL), where clients train models in a sequential manner.
no code implementations • 29 Mar 2023 • Zeju Li, Xinghan Liu, Guoshun Nan, Jinfei Zhou, Xinchen Lyu, Qimei Cui, Xiaofeng Tao
To this end, we present SemBLK, a novel method that can learn to generate destructive physical layer semantic attacks for an ESC system under the black-box setting, where the adversaries are imperceptible to humans.
no code implementations • 3 Feb 2023 • Yipeng Li, Xinchen Lyu
In this paper, we derive the convergence guarantees of Sequential SL (SSL, the vanilla case of SL that conducts the model training in sequence) for strongly/general/non-convex objectives on heterogeneous data.
no code implementations • 10 Mar 2022 • Junlin Liu, Xinchen Lyu, Qimei Cui, Xiaofeng Tao
We mathematically analyze the potential label leakages and propose the cosine and Euclidean similarity measurements for gradients and smashed data, respectively.