416 citations
- IBM (United States)US5 papers
- Massachusetts Institute of TechnologyUS4 papers
- University of MichiganUS3 papers
- ETH ZurichCH2 papers
- Microsoft Research (United Kingdom)GB2 papers
- Advanced Micro Devices (United States)US1 paper
- Columbia UniversityUS1 paper
- Consejo Superior de Investigaciones CientíficasES1 paper
- Duke UniversityUS1 paper
- Financial Research (Hungary)HU1 paper
- Georgia State UniversityUS1 paper
- IBM Research - AlmadenUS1 paper
8 papers · 1 filter
Distributed Adversarial Training to Robustify Deep Neural Networks at Scale
Gaoyuan Zhang, Songtao Lu, Yihua Zhang +7
Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against…
Individually Fair Gradient Boosting
Alexander Vargo, Fan Zhang, Mikhail Yurochkin +1
We consider the task of enforcing individual fairness in gradient boosting. Gradient boosting is a popular method for machine learning from tabular data, which arise often in appli…
Generating Adversarial Computer Programs using Optimized Obfuscations
Shashank Srikant, Sijia Liu, Tamara Mitrovska +4
Machine learning (ML) models that learn and predict properties of computer programs are increasingly being adopted and deployed. These models have demonstrated success in applicati…
Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples
Washington Garcia, Pin-Yu Chen, Somesh Jha +2
Designing deep networks robust to adversarial examples remains an open problem. Likewise, recent zeroth order hard-label attacks on image classification models have shown comparabl…
Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations
Yu-Lin Tsai, Chia-Yi Hsu, Chia-Mu Yu +1
Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to…
Adam: A Stochastic Method with Adaptive Variance Reduction
Mingrui Liu, Wei Zhang, Francesco Orabona +1
Adam is a widely used stochastic optimization method for deep learning applications. While practitioners prefer Adam because it requires less parameter tuning, its use is problemat…