Paper proposes a new black-box adversarial attack for clustering models.
problem Adversarial attacks on clustering algorithms are overlooked.
method Perturbs a single sample close to the decision boundary to miscluster multiple samples.
result The attack can miscluster multiple samples without knowing the true metric.
ClusTR improves clustering-based models' robustness without adversarial training.
problem Improving clustering-based models' robustness.
method Proposes ClusTR, a clustering-based training framework for robust models without adversarial training.
result ClusTR outperforms adversarially-trained models by up to 4% under strong PGD attacks.
Nowadays more and more data are gathered for detecting and preventing cyber attacks. In cyber security applications, data analytics techniques have to deal with active adversaries that try to deceive the data analytics models and avoid being detected. The existence of such adversarial behavior motivates the development…
Paper presents strong black-box attacks on unsupervised clustering models.
problem Adversarial attacks on unsupervised machine learning models.
method Iterative black-box attack on clustering algorithms.
result Adversarial samples can fool clustering algorithms irrespective of the algorithm used.
ADEC addresses feature randomness and drift in autoencoder-based clustering.
problem Clustering autoencoders learn unreliable pseudo-labels, distorting latent space and feature randomness.
method Adversarial training to balance reconstruction loss and clustering objective.
result ADEC outperforms state-of-the-art autoencoder-based clustering methods.
ARMED models improve deep learning interpretability and generalize better on clustered data.
problem Clustered data leads to spurious associations and poor model fitting.
method Adversarial regularization and mixed effects subnetworks.
result ARMED models outperform conventional methods in accuracy and generalization.
Proposes a black-box attack to test clustering algorithms' robustness.
problem Testing robustness of clustering algorithms against adversarial noise.
method Formulates as a constrained minimization problem, uses custom AGA for optimization.
result Demonstrates sensitivity of clustering algorithms to adversarial samples.
Improves deep learning robustness by enforcing local and global compactness.
problem Deep neural networks' vulnerability to adversarial attacks.
method Proposes Adversary Divergence Reduction Network (ADRN) that enforces local/global compactness and clustering assumption.
result Augmenting adversarial training with ADRN components improves robustness.
Paper tackles Byzantine attacks in Federated Learning by clustering and robustifying.
problem Adversarial attacks from Byzantine machines in Federated Learning.
method Iterative Federated Clustering Algorithm (IFCA) with trimmed mean and median aggregation.
result Improved convergence rate for strongly convex loss functions in Byzantine-Robust IFCA.
Spectral clustering is robust to helpful model changes but not to random changes.
problem Robustness of spectral clustering in the presence of semirandom adversaries.
method Analysis of spectral clustering algorithms under semirandom adversaries.
result Spectral clustering with unnormalized Laplacian is strongly consistent under semirandom adversaries.
Clustering algorithms have been increasingly adopted in security applications to spot dangerous or illicit activities. However, they have not been originally devised to deal with deliberate attack attempts that may aim to subvert the clustering process itself. Whether clustering can be safely adopted in such settings r…
Paper proposes a novel adversarial framework for graph embedding.
problem Graph embedding often fails to represent latent codes effectively.
method Adversarial training to enforce latent codes to match a prior distribution.
result ARGA and ARVGA models improve graph embedding for link prediction and clustering.
Generative Adversarial networks (GANs) have obtained remarkable success in many unsupervised learning tasks and unarguably, clustering is an important unsupervised learning problem. While one can potentially exploit the latent-space back-projection in GANs to cluster, we demonstrate that the cluster structure is not re…
Study exact partition recovery with same-cluster oracle, bounded error.
problem Exact recovery of partitions with same-cluster oracle in adversarial error.
method Novel connection to correlation clustering, Rényi-Ulam framework, upper and lower bounds, randomized algorithm analysis, adaptivity-query complexity study.
result Upper and lower bounds on worst-case query complexity, expected performance bounds of randomized algorithm.
The Adversarially Learned Mixture Model (AMM) is a generative model for unsupervised or semi-supervised data clustering. The AMM is the first adversarially optimized method to model the conditional dependence between inferred continuous and categorical latent variables. Experiments on the MNIST and SVHN datasets show t…
Paper presents robust clustering methods for general mixture models.
problem Clustering with sub-Gaussian error assumptions often invalid in practice.
method Hybrid clustering with robust centroid estimate and data-driven initialization.
result Provably near-optimal mislabeling guarantees for general error distributions.
New algorithm clusters networks with outliers, achieving exact recovery.
problem Clustering networks with outliers and degree corrections.
method Convex optimization with a penalization term for positive deviations.
result Achieves exact recovery of clusters under mild conditions.
MMGAN stabilizes GANs for multi-modal data clustering.
problem Stability and data distribution loss in GANs for multi-modal data.
method Model latent space as Gaussian mixture model, clusters data manifolds, and trains with clustering network.
result MMGAN outperforms state-of-the-art models in clustering multi-modal data.
MetalGAN uses meta-learning and clustering to colorize images with little data.
problem Colorizing images with limited data.
method Adversarial training and meta-learning with cluster-based dataset division.
result The method achieves high-quality colorization with minimal data.
Survey of graph adversarial learning tasks and their attacks and defenses.
problem Uncertainty and unreliability of deep learning models on graphs against adversarial examples.
method Unified problem definition and comprehensive review of existing works.
result Unified definitions and taxonomies for graph adversarial learning tasks.
Adaptive framework generates challenging adversarial scenarios for autonomous vehicles.
problem Lack of efficient and adaptable evaluation methods for autonomous vehicles.
method Adaptive evaluation framework using ensemble models and nonparametric Bayesian clustering.
result Adversarial scenarios significantly degrade tested autonomous vehicles' performance.
Gradient flow in ReLU networks biases towards generalization but makes them vulnerable to adversarial attacks.
problem Generalization vs. Adversarial Robustness in ReLU Networks
method Analysis of gradient flow in two-layer ReLU networks with clustered data.
result Gradient flow biases towards generalization but also makes networks vulnerable to adversarial attacks.
Softmax and k-means clustering are mathematically linked, improving neural network robustness.
problem Improving neural network robustness against adversarial attacks.
method Formally proving the connection between softmax and k-means, proposing Centroid Based Tailoring.
result The proposed Gauss network is less susceptible to one-pixel attacks.
Recent developments in specialized computer hardware have greatly accelerated atomic level Molecular Dynamics (MD) simulations. A single GPU-attached cluster is capable of producing microsecond-length trajectories in reasonable amounts of time. Multiple protein states and a large number of microstates associated with f…
Gradient-trained shallow networks can generalize well but are vulnerable to small-radius adversarial attacks.
problem Adversarial robustness of gradient-trained shallow networks.
method Analysis of neuron alignment and polynomial ReLU activation.
result Gradient-trained shallow networks with polynomial ReLU activation are robust to small-radius adversarial attacks.
Improves domain adaptation by clustering target representations.
problem Learning invariant and discriminative representations for unlabeled target domains.
method Simultaneously learns tightly clustered target representations and assigns each cluster to a unique class from the source.
result Achieves state-of-the-art performance in balanced, imbalanced, and partial domain adaptation.
Paper finds a latent k−polytope in data efficiently.
problem Finding a latent k−polytope in data points. method Algorithm using subset smoothed polytope to estimate k−polytope. result Algorithm runs in O∗(k⋅extnnz) time, efficient even for sparse data. Paper introduces a method for learning interpretable disentangled representations using adversarial VAEs.
problem Learning interpretable and disentangled feature representations in medical applications.
method Adversarial Variational Autoencoder with total correlation constraint.
result The learned disentangled representation is interpretable and superior to state-of-the-art methods, showing improvements in disentanglement, clustering, and classification.
In this paper, we consider a generic probabilistic discriminative learner from the functional viewpoint and argue that, to make it learn well, it is necessary to constrain its hypothesis space to a set of non-trivial piecewise constant functions. To achieve this goal, we present a scalable unsupervised regularization f…
Adversarial training improves graph autoencoder generalization.
problem Improving graph autoencoder generalization.
method Formulated L2 and L1 adversarial training for graph autoencoders and variational graph autoencoders.
result Adversarial training boosts graph autoencoder and variational graph autoencoder generalization.
ABoB optimizes online configuration tuning by clustering parameters and accelerating learning.
problem Online optimization in large, dynamic parameter spaces.
method Hierarchical adversarial bandit framework.
result Significant performance gains in adversarial metric scenarios.
Designing a logo for a new brand is a lengthy and tedious back-and-forth process between a designer and a client. In this paper we explore to what extent machine learning can solve the creative task of the designer. For this, we build a dataset -- LLD -- of 600k+ logos crawled from the world wide web. Training Generati…
Domain adaptation refers to the problem of leveraging labeled data in a source domain to learn an accurate model in a target domain where labels are scarce or unavailable. A recent approach for finding a common representation of the two domains is via domain adversarial training (Ganin & Lempitsky, 2015), which attempt…
Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtain meaningful representations of 3D shapes that can be used for challenging tasks including 3D points generation, reconstruction, compression…
YuruGAN generates yuru-chara images using GANs and clustering for small datasets.
problem Generating high-quality yuru-chara images with limited data.
method Class conditional GAN with clustering and data augmentation.
result Improved quality of generated yuru-chara images through clustering and data augmentation.
We provide an approach for learning deep neural net representations of models described via conditional moment restrictions. Conditional moment restrictions are widely used, as they are the language by which social scientists describe the assumptions they make to enable causal inference. We formulate the problem of est…
This paper considers the problem of subspace clustering under noise. Specifically, we study the behavior of Sparse Subspace Clustering (SSC) when either adversarial or random noise is added to the unlabelled input data points, which are assumed to be in a union of low-dimensional subspaces. We show that a modified vers…
MadNet uses MAD optimization to enhance deep model robustness against adversarial attacks.
problem Defending deep models against adversarial attacks.
method Inspired by certificate defense, MAD optimization increases separability of class clusters and decreases sensitivity to small distortions.
result MadNet improves adversarial robustness compared to state-of-the-art methods.
Subspace clustering is the problem of clustering data points into a union of low-dimensional linear/affine subspaces. It is the mathematical abstraction of many important problems in computer vision, image processing and machine learning. A line of recent work (4, 19, 24, 20) provided strong theoretical guarantee for s…
Improved clustering algorithm with random center count.
problem Worst-case approximation ratio of k-means++. method Randomizes the number of centers in k-means++. result An O(1)-approximation with constant probability. Adversarial online multi-task RL with task separation.
problem Minimize regret in an adversarial online multi-task setting with unknown MDPs.
method Prove minimax and instance-specific lower bounds, develop a clustering algorithm with optimal sample complexity and regret.
result Tight sample complexity and regret bounds for adversarial online multi-task RL.
Generative Adversarial Networks improve credit card fraud detection.
problem Detecting fraudulent credit card transactions accurately.
method Using GANs to generate synthetic data for oversampling.
result Wasserstein-GAN produces more realistic fraudulent transactions.
Paper examines vulnerabilities in data-driven pricing schemes.
problem Vulnerability of clustering-oriented pricing schemes to malicious user behavior.
method Defined a notion of disguising to identify strategic behaviors of malicious users, characterized sensitivity zones to evaluate malicious user percentages, conducted cost benefit analysis.
result Concluded with a vulnerability analysis of data-driven pricing schemes.
In this paper we present a method for learning a discriminative classifier from unlabeled or partially labeled data. Our approach is based on an objective function that trades-off mutual information between observed examples and their predicted categorical class distribution, against robustness of the classifier to an …
This work uses image generation models to find vision model bugs.
problem Automatically discovering failures in vision models.
method Conditional text-to-image generation and captioning models.
result Demonstrated utility of large-scale generative models to find vision model bugs.
Many state-of-the-art machine learning models such as deep neural networks have recently shown to be vulnerable to adversarial perturbations, especially in classification tasks. Motivated by adversarial machine learning, in this paper we investigate the robustness of sparse regression models with strongly correlated co…
This paper explores how the latent structure affects clustering in GAN-generated data.
problem Achieving well-clustered data in GAN-generated spaces, especially with class imbalance.
method Derives conditions for faithful clustering in GANs, including multimodal latent space, latent space inversion, and cluster priors imposition.
result Necessary and sufficient conditions for clustering in GANs are identified, and their importance is demonstrated through ablative studies.
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the laten…