2 citations · 5 across the 18 of their papers we have counts for
7 papers · 1 filter
Towards Strong Certified Defense with Universal Asymmetric Randomization
Hanbin Hong, Ashish Kundu, Ali Payani +2
Randomized smoothing has become essential for achieving certified adversarial robustness in machine learning models. However, current methods primarily use isotropic noise distribu…
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models
Haozheng Luo, Chenghao Qiu, Yimin Wang +9
We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first compre…
FedTilt: Towards Multi-Level Fairness-Preserving and Robust Federated Learning
Binghui Zhang, Luis Mares De La Cruz, Binghui Wang
Federated Learning (FL) is an emerging decentralized learning paradigm that can partly address the privacy concern that cannot be handled by traditional centralized and distributed…
Learning Robust and Privacy-Preserving Representations via Information Theory
Binghui Zhang, Sayedeh Leila Noorbakhsh, Yun Dong +2
Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to miti…
Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
Shuya Feng, Meisam Mohammady, Hanbin Hong +4
Differentially private federated learning (DP-FL) is a promising technique for collaborative model training while ensuring provable privacy for clients. However, optimizing the tra…
Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks
Sayedeh Leila Noorbakhsh, Binghui Zhang, Yuan Hong +1
Machine learning (ML) is vulnerable to inference (e.g., membership inference, property inference, and data reconstruction) attacks that aim to infer the private information of trai…
Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
Hanbin Hong, Xinyu Zhang, Binghui Wang +2
Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a…