One Train for Two Tasks: An Encrypted Traffic Classification Framework Using...
As network security receives widespread attention, encrypted traffic classification has become the current research focus. However, existing methods conduct traffic classification without sufficiently...
View ArticleAccelerated Smoothing: A Scalable Approach to Randomized Smoothing
Randomized smoothing has emerged as a potent certifiable defense against adversarial attacks by employing smoothing noises from specific distributions to ensure the robustness of a smoothed classifier....
View ArticleUnderstanding Deep Learning defenses Against Adversarial Examples Through...
In recent years, Deep Neural Network models have been developed in different fields, where they have brought many advances. However, they have also started to be used in tasks where risk is critical. A...
View ArticleScore-based Diffusion Models via Stochastic Differential Equations -- a...
This is an expository article on the score-based diffusion models, with a particular focus on the formulation via stochastic differential equations (SDE). After a gentle introduction, we discuss the...
View ArticleTopological Safeguard for Evasion Attack based on the Interpretability of...
In the last years, Deep Learning technology has been proposed in different fields, bringing many advances in each of them, but identifying new threats in these solutions regarding cybersecurity. Those...
View ArticleDifferentially Private Decentralized Learning with Random Walks
The popularity of federated learning comes from the possibility of better scalability and the ability for participants to keep control of their data, improving data security and sovereignty....
View ArticleScore-Based Physics-Informed Neural Networks for High-Dimensional...
The Fokker-Planck (FP) equation is a foundational PDE in stochastic processes. However, curse of dimensionality (CoD) poses challenge when dealing with high-dimensional FP PDEs. Although Monte Carlo...
View ArticleOn the Distance from Calibration in Sequential Prediction
We study a sequential binary prediction setting where the forecaster is evaluated in terms of the calibration distance, which is defined as the $L_1$ distance between the predicted values and the set...
View ArticleBandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
Consider the domain of multiclass classification within the adversarial online setting. What is the price of relying on bandit feedback as opposed to full information? To what extent can an adaptive...
View ArticleThe I/O Complexity of Attention, or How Optimal is Flash Attention?
Self-attention is at the heart of the popular Transformer architecture, yet suffers from quadratic time and memory complexity. The breakthrough FlashAttention algorithm revealed I/O complexity as the...
View ArticleConditional Generative Models are Sufficient to Sample from Any Causal Effect...
Causal inference from observational data has recently found many applications in machine learning. While sound and complete algorithms exist to compute causal effects, many of these algorithms require...
View ArticleContext-aware Multi-Model Object Detection for Diversely Heterogeneous...
In recent years, deep neural networks (DNNs) have gained widespread adoption for continuous mobile object detection (OD) tasks, particularly in autonomous systems. However, a prevalent issue in their...
View ArticleAuxiliary Reward Generation with Transition Distance Representation Learning
Reinforcement learning (RL) has shown its strength in challenging sequential decision-making problems. The reward function in RL is crucial to the learning performance, as it serves as a measure of the...
View ArticlePotential-Based Reward Shaping For Intrinsic Motivation
Recently there has been a proliferation of intrinsic motivation (IM) reward-shaping methods to learn in complex and sparse-reward environments. These methods can often inadvertently change the set of...
View ArticleDiff-RNTraj: A Structure-aware Diffusion Model for Road Network-constrained...
Trajectory data is essential for various applications as it records the movement of vehicles. However, publicly available trajectory datasets remain limited in scale due to privacy concerns, which...
View ArticleAssessing Generalization for Subpopulation Representative Modeling via...
This study evaluates the ability of Large Language Model (LLM)-based Subpopulation Representative Models (SRMs) to generalize from empirical data, utilizing in-context learning with data from the 2016...
View ArticleBayesian Federated Learning Via Expectation Maximization and Turbo Deep...
Federated learning (FL) is a machine learning paradigm where the clients possess decentralized training data and the central server handles aggregation and scheduling. Typically, FL algorithms involve...
View ArticleA Novel Gaussian Min-Max Theorem and its Applications
A celebrated result by Gordon allows one to compare the min-max behavior of two Gaussian processes if certain inequality conditions are met. The consequences of this result include the Gaussian min-max...
View ArticleData Distribution-based Curriculum Learning
The order of training samples can have a significant impact on the performance of a classifier. Curriculum learning is a method of ordering training samples from easy to hard. This paper proposes the...
View ArticleAccuracy of TextFooler black box adversarial attacks on 01 loss sign...
Recent work has shown the defense of 01 loss sign activation neural networks against image classification adversarial attacks. A public challenge to attack the models on CIFAR10 dataset remains...
View Article