Adversarial vulnerability bounds for Gaussian process classification
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
We present an analysis of the SwissCovid application which is currently being tested. We observe that the essential part of SwissCovid is under the control of Apple and Google. Outsourcing the heart of SwissCovid to Apple and Google has apparent benefits i ...
Security system designers favor worst-case security metrics, such as those derived from differential privacy (DP), due to the strong guarantees they provide. On the downside, these guarantees result in a high penalty on the system's performance. In this pa ...
Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when deployed in noisy envi ...
Random Fourier features (RFFs) provide a promising way for kernel learning in a spectral case. Current RFFs-based kernel learning methods usually work in a two-stage way. In the first-stage process, learn-ing an optimal feature map is often formulated as a ...
The ab initio determination of electronic excited state (ES) properties is the cornerstone of theoretical photochemistry. Yet, traditional ES methods become impractical when applied to fairly large molecules, or when used on thousands of systems. Machine l ...
Background and objective: To automatically identify patients with diabetes mellitus (DM) who have high risk of developing diabetic foot, via an unsupervised machine learning technique. Methods: We collected a new database containing 54 known risk factors f ...
Neighborhood-scale projects often commence with the conceptualization of several massing-schemes as potential design solutions. There is growing interest in using building performance simulation (BPS) to evaluate and rank such conceptual stage schemes in o ...
Modern machine learning tools have shown promise in detecting symptoms of neurological disorders. However, current approaches typically train a unique classifier for each subject. This subject-specific training scheme requires long labeled recordings from ...
We analyze the influence of adversarial training on the loss landscape of machine learning models. To this end, we first provide analytical studies of the properties of adversarial loss functions under different adversarial budgets. We then demonstrate tha ...
Recently, Kannan et al. [2018] proposed several logit regularization methods to improve the adversarial robustness of classifiers. We show that the computationally fast methods they propose - Clean Logit Pairing (CLP) and Logit Squeezing (LSQ) - just make ...
