134 citations · 419 across the 67 of their papers we have counts for
13 papers · 1 filter
Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization
Arezoo Rajabi, Reeya Pimple, Aiswarya Janardhanan +3
Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce…
Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning
Zhangchen Xu, Fengqing Jiang, Luyao Niu +2
Federated learning (FL) enables multiple participants to train a global machine learning model without sharing their private training data. Peer-to-peer (P2P) FL advances existing…
LDL: A Defense for Label-Based Membership Inference Attacks
Arezoo Rajabi, Dinuka Sahabandu, Luyao Niu +2
The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitt…
Game of Trojans: A Submodular Byzantine Approach
Dinuka Sahabandu, Arezoo Rajabi, Luyao Niu +3
Machine learning models in the wild have been shown to be vulnerable to Trojan attacks during training. Although many detection mechanisms have been proposed, strong adaptive attac…
Privacy-Preserving Reinforcement Learning Beyond Expectation
Arezoo Rajabi, Bhaskar Ramasubramanian, Abdullah Al Maruf +1
Cyber and cyber-physical systems equipped with machine learning algorithms such as autonomous cars share environments with humans. In such a setting, it is important to align syste…
Reinforcement Learning Beyond Expectation
Bhaskar Ramasubramanian, Luyao Niu, Andrew Clark +1
The inputs and preferences of human users are important considerations in situations where these users interact with autonomous cyber or cyber-physical systems. In these scenarios,…
Shaping Advice in Deep Multi-Agent Reinforcement Learning
Baicen Xiao, Bhaskar Ramasubramanian, Radha Poovendran
Multi-agent reinforcement learning involves multiple agents interacting with each other and a shared environment to complete tasks. When rewards provided by the environment are spa…
Are Odds Really Odd? Bypassing Statistical Detection of Adversarial Examples
Hossein Hosseini, Sreeram Kannan, Radha Poovendran
Deep learning classifiers are known to be vulnerable to adversarial examples. A recent paper presented at ICML 2019 proposed a statistical test detection method based on the observ…
Potential-Based Advice for Stochastic Policy Learning
Baicen Xiao, Bhaskar Ramasubramanian, Andrew Clark +3
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show…
Dropping Pixels for Adversarial Robustness
Hossein Hosseini, Sreeram Kannan, Radha Poovendran
Deep neural networks are vulnerable against adversarial examples. In this paper, we propose to train and test the networks with randomly subsampled images with high drop rates. We…
Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
Hossein Hosseini, Yize Chen, Sreeram Kannan +2
Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars. To further broa…
Deceiving Google's Perspective API Built for Detecting Toxic Comments
Hossein Hosseini, Sreeram Kannan, Baosen Zhang +1
Social media platforms provide an environment where people can freely engage in discussions. Unfortunately, they also enable several problems, such as online harassment. Recently,…
Learning Temporal Dependence from Time-Series Data with Latent Variables
Hossein Hosseini, Sreeram Kannan, Baosen Zhang +1
We consider the setting where a collection of time series, modeled as random processes, evolve in a causal manner, and one is interested in learning the graph governing the relatio…