-
EnCoD: Distinguishing Compressed and Encrypted File Fragments
A large, standardized dataset of encrypted and compressed fragments covering various popular file formats and fragment sizes. -
MapAI: Precision in building segmentation
The dataset used in this paper for building extraction from LiDAR data and aerial images. -
Pendulum Control Dataset
The dataset used in the paper is a collection of data points from a pendulum system, where the pendulum is controlled using a policy computed via Algorithm 1. The dataset is... -
High Throughput Training of Deep Surrogates from Large Ensemble Runs
The dataset used in this paper is a large ensemble run of simulations for training deep surrogates. -
MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of B...
A large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations. -
Clusters in Explanation Space: Inferring disease subtypes from model explanat...
Four datasets: synthetic, Fashion-MNIST, UK Biobank brain imaging, and Cancer Genome Atlas. -
Defensive ML: Defending Architectural Side-channels with Adversarial Obfuscation
The dataset used in the paper is a memory contention side-channel attack and an application power side-channel attack. -
Stateful Performative Gradient Descent
The dataset used in the paper is a stateful performative setting, where the data distribution reacts to the deployed model. The goal is to learn a model that both induces a... -
Differentiable Triage
The dataset used in the paper is a synthetic dataset for supervised learning under algorithmic triage. -
Determinantal Point Process
The Determinantal Point Process (DPP) is a probabilistic model of mimicking particles with repulsive interactions in theoretical quantum physics. -
Multiple-criteria Based Active Learning with Fixed-size Determinantal Point P...
Active learning aims to achieve greater accuracy with less training data by selecting the most useful data samples from which it learns. -
Individual health–disease phase diagrams for disease prevention based on mach...
The health–disease phase diagram (HDPD) represents individual health status at each time point by visualizing the boundary values of multiple biomarkers that fluctuate early in... -
GPU-based Private Information Retrieval for On-Device Machine Learning Inference
The authors propose a system for efficiently and privately serving embeddings for on-device ML applications. -
EUROCROPSML: A Time Series Benchmark Dataset
EUROCROPSML is an analysis-ready remote sensing machine learning dataset for time series crop type classification of agricultural parcels in Europe. -
Overparametrised Shallow ReLU Networks
The dataset used in the paper is a high-dimensional dataset for supervised learning, with a focus on shallow neural networks and overparametrization. -
A4: Actionable Adversarial Attack
A4: Actionable Adversarial Attack to evade AdGraph, a state-of-the-art learning-based adblocker. -
SUSY Dataset
The dataset used in the paper is the SUSY dataset for logistic regression. -
COV1 Dataset
The dataset used in the paper is the COV1 dataset for hinge loss minimization. -
Ridge Regression Dataset
The dataset used in the paper is a synthetic dataset for ridge regression problem over a network of agents, modeled as a Erdos-Renyi graph with m = 30 nodes and edge probability... -
Margin pursuit by steepest descent
Binary classification on real-world data sets, modified to control for unbalanced ratios of positive and negative labels.
