31 citations · 71 across the 12 of their papers we have counts for
5 papers · 1 filter
Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access
Akshaj Kumar Veldanda, Ivan Brugere, Sanghamitra Dutta +2
Fair machine learning methods seek to train models that balance model performance across demographic subgroups defined over sensitive attributes like race and gender. Although sens…
Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale
Akshaj Kumar Veldanda, Ivan Brugere, Jiahao Chen +3
The success of DNNs is driven by the counter-intuitive ability of over-parameterized networks to generalize, even when they perfectly fit the training data. In practice, test error…
Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection
Hao Fu, Akshaj Kumar Veldanda, Prashanth Krishnamurthy +2
This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is…
On Evaluating Neural Network Backdoor Defenses
Akshaj Veldanda, Siddharth Garg
Deep neural networks (DNNs) demonstrate superior performance in various fields, including scrutiny and security. However, recent studies have shown that DNNs are vulnerable to back…
CryptoNAS: Private Inference on a ReLU Budget
Zahra Ghodsi, Akshaj Veldanda, Brandon Reagen +1
Machine learning as a service has given raise to privacy concerns surrounding clients' data and providers' models and has catalyzed research in private inference (PI): methods to p…