Search Results for author:
Found 25 papers, 10 papers with code
Semi-Crowdsourced Clustering: Generalizing Crowd Labeling by Robust Distance Metric Learning
One difficulty in learning the pairwise similarity measure is that there is a significant amount of noise and inter-worker variations in the manual annotations obtained via crowdsourcing.
Scalable Demand-Aware Recommendation
In particular for durable goods, time utility is a function of inter-purchase duration within product category because consumers are unlikely to purchase two items in the same category in close temporal succession.
Negative-Unlabeled Tensor Factorization for Location Category Inference from Highly Inaccurate Mobility Data
In order to efficiently solve the proposed framework, we propose a parameter-free and scalable optimization algorithm by effectively exploring the sparse and low-rank structure of the tensor.
Characterizing Attacks on Deep Reinforcement Learning
To the best of our knowledge, we are the first to apply adversarial attacks on DRL systems to physical robots.
Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System
Existing work addresses this issue with Inverse Propensity Weighting (IPW), which decreases the impact of popular items on the training and increases the impact of long-tail items.
On the Limitations of Denoising Strategies as Adversarial Defenses
Surprisingly, our experimental results show that even if most of the perturbations in each dimension is eliminated, it is still difficult to obtain satisfactory robustness.
With False Friends Like These, Who Can Notice Mistakes?
In this paper, we unveil the threat of hypocritical examples -- inputs that are originally misclassified yet perturbed by a false friend to force correct predictions.
Learning Contextual Perturbation Budgets for Training Robust Neural Networks
We also demonstrate that the perturbation budget generator can produce semantically-meaningful budgets, which implies that the generator can capture contextual information and the sensitivity of different features in a given image.
Robust Text CAPTCHAs Using Adversarial Examples
At the second stage, we design and apply a highly transferable adversarial attack for text CAPTCHAs to better obstruct CAPTCHA solvers.
Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
Delusive attacks aim to substantially deteriorate the test accuracy of the learning model by slightly perturbing the features of correctly labeled training examples.
On the Adversarial Robustness of Vision Transformers
Following the success in advancing natural language processing and understanding, transformers are expected to bring revolutionary changes to computer vision.
Fast Certified Robust Training with Short Warmup
Despite that state-of-the-art (SOTA) methods including interval bound propagation (IBP) and CROWN-IBP have per-batch training complexity similar to standard neural network training, they usually use a long warmup schedule with hundreds or thousands epochs to reach SOTA performance and are thus still costly.
A Simple yet Universal Strategy for Online Convex Optimization
In this paper, we propose a simple strategy for universal online convex optimization, which avoids these limitations.
Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation
Hence, the key is to make full use of rich interaction information among streamers, users, and products.
Towards Heterogeneous Clients with Elastic Federated Learning
Training in heterogeneous and potentially massive networks introduces bias into the system, which is originated from the non-IID data and the low participation rate in reality.
Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
Recently, there has been a line of work on incorporating the formal privacy notion of differential privacy with FL.
Training Meta-Surrogate Model for Transferable Adversarial Attack
In this paper, we tackle this problem from a novel angle -- instead of using the original surrogate models, can we obtain a Meta-Surrogate Model (MSM) such that attacks to this model can be easier transferred to other models?
Trustworthy AI: From Principles to Practices
In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems.
Adversarial Attack across Datasets
In this paper, we define a Generalized Transferable Attack (GTA) problem where the attacker doesn't know this information and is acquired to attack any randomly encountered images that may come from unknown datasets.
How and When Adversarial Robustness Transfers in Knowledge Distillation?
Our comprehensive analysis shows several novel insights that (1) With KDIGA, students can preserve or even exceed the adversarial robustness of the teacher model, even when their models have fundamentally different architectures; (2) KDIGA enables robustness to transfer to pre-trained students, such as KD from an adversarially trained ResNet to a pre-trained ViT, without loss of clean accuracy; and (3) Our derived local linearity bounds for characterizing adversarial robustness in KD are consistent with the empirical results.
Federated Two-stage Learning with Sign-based Voting
In this paper, we design a federated two-stage learning framework that augments prototypical federated learning with a cut layer on devices and uses sign-based stochastic gradient descent with the majority vote method on model updates.
On the Convergence and Robustness of Adversarial Training
In this paper, we propose such a criterion, namely First-Order Stationary Condition for constrained optimization (FOSC), to quantitatively evaluate the convergence quality of adversarial examples found in the inner maximization.
Can Adversarial Training Be Manipulated By Non-Robust Features?
Under this threat, we show that adversarial training using a conventional defense budget $\epsilon$ provably fails to provide test robustness in a simple statistical setting, where the non-robust features of the training data can be reinforced by $\epsilon$-bounded perturbation.
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
To tackle this problem, we next propose to prepend an autoencoder (AE) to a given (black-box) model so that DS can be trained using variance-reduced ZO optimization.
Smoothed Online Convex Optimization Based on Discounted-Normal-Predictor
In this paper, we investigate an online prediction strategy named as Discounted-Normal-Predictor (Kapralov and Panigrahy, 2010) for smoothed online convex optimization (SOCO), in which the learner needs to minimize not only the hitting cost but also the switching cost.
