18 citations · 75 across the 11 of their papers we have counts for
7 papers · 1 filter
DHBE: Data-free Holistic Backdoor Erasing in Deep Neural Networks via Restricted Adversarial Distillation
Zhicong Yan, Shenghong Li, Ruijie Zhao +2
Backdoor attacks have emerged as an urgent threat to Deep Neural Networks (DNNs), where victim DNNs are furtively implanted with malicious neurons that could be triggered by the ad…
Towards Return Parity in Markov Decision Processes
Jianfeng Chi, Jian Shen, Xinyi Dai +3
Algorithmic decisions made by machine learning models in high-stakes domains may have lasting impacts over time. However, naive applications of standard fairness criterion in stati…
Meta Federated Learning
Omid Aramoon, Pin-Yu Chen, Gang Qu +1
Due to its distributed methodology alongside its privacy-preserving features, Federated Learning (FL) is vulnerable to training time adversarial attacks. In this study, our focus i…
Understanding and Mitigating Accuracy Disparity in Regression
Jianfeng Chi, Yuan Tian, Geoffrey J. Gordon +1
With the widespread deployment of large-scale prediction systems in high-stakes domains, e.g., face recognition, criminal justice, etc., disparity in prediction accuracy between di…
Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning
Syed Zawad, Ahsan Ali, Pin-Yu Chen +5
Data heterogeneity has been identified as one of the key features in federated learning but often overlooked in the lens of robustness to adversarial attacks. This paper focuses on…
Model-Targeted Poisoning Attacks with Provable Convergence
Fnu Suya, Saeed Mahloujifar, Anshuman Suri +2
In a poisoning attack, an adversary with control over a small fraction of the training data attempts to select that data in a way that induces a corrupted model that misbehaves in…
Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
Han Zhao, Jianfeng Chi, Yuan Tian +1
Crowdsourced data used in machine learning services might carry sensitive information about attributes that users do not want to share. Various methods have been proposed to minimi…