Showing cs.LGShow all
3 papers · 1 filter
cs.LG2024
BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
Zhengyuan Jiang, Xingyu Lyu, Shanghao Shi +5
Federated learning, while being a promising approach for collaborative model training, is susceptible to backdoor attacks due to its decentralized nature. Backdoor attacks have sho…
cs.LG2024
Let the Noise Speak: Harnessing Noise for a Unified Defense Against Adversarial and Backdoor Attacks
Md Hasan Shahriar, Ning Wang, Naren Ramakrishnan +2
The exponential adoption of machine learning (ML) is propelling the world into a future of distributed and intelligent automation and data-driven solutions. However, the proliferat…
cs.LG2023
Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction
Shanghao Shi, Ning Wang, Yang Xiao +4
Federated learning is known for its capability to safeguard the participants' data privacy. However, recently emerged model inversion attacks (MIAs) have shown that a malicious par…