Adversarial examples are delicately perturbed inputs, which aim to mislead machine learning models towards incorrect outputs. While most of the existing work focuses on generating adversarial perturbations in multi-class classification problems, many real-world applications fall into the multi-label setting in which on…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “label perturbations”
Introduces TPV to analyze model robustness without labels.
problem Analyzing post-training robustness of machine learning models.
method Parameter perturbations and test prediction variance (TPV) as a unifying framework.
result TPV connects various perturbations under a single lens, providing insights into model stability.
Wide networks learn from adversarial perturbations effectively.
problem Understanding why adversarial examples deceive classifiers and transfer between models.
method Assumed wide two-layer networks, proved with theoretical analysis.
result Adversarial perturbations contain class-specific features for networks to generalize.
A new PLL method uses class activation values to improve robustness.
problem Weakly supervised learning with noisy data and adversarial perturbations.
method Subjective logic with class activation values for uncertainty representation and label weight re-distribution.
result More robust predictions under high noise levels, out-of-distribution examples, and adversarial perturbations.
ALPS improves neural network robustness and generalization.
problem Challenges in designing effective regularization schemes for adversarial robustness.
method Adversarial Labelling of Perturbed Samples (ALPS) using synthetic samples and min-max formulation.
result ALPS achieves state-of-the-art regularization performance and adversarial robustness.
Label noise in adversarial training leads to robust overfitting, explained and mitigated.
problem Label noise in adversarial training causes robust overfitting.
method Proposed a method to automatically calibrate labels.
result Consistent performance improvements across various models and datasets.
New geometric interpretation explains over-parameterized models and adversarial perturbations.
problem Geometric understanding of over-parameterized regression and adversarial perturbations.
method Alternative geometric interpretation of regression in feature space.
result Adversarial perturbations are a natural feature of biased models due to underlying geometry.
We present CROSSGRAD, a method to use multi-domain training data to learn a classifier that generalizes to new domains. CROSSGRAD does not need an adaptation phase via labeled or unlabeled data, or domain features in the new domain. Most existing domain adaptation methods attempt to erase domain signals using technique…
We study the problem of finding a universal (image-agnostic) perturbation to fool machine learning (ML) classifiers (e.g., neural nets, decision tress) in the hard-label black-box setting. Recent work in adversarial ML in the white-box setting (model parameters are known) has shown that many state-of-the-art image clas…
Proposes a robust VIB approach using soft labels and mutual info estimation.
problem Improving robustness of VIB to adversarial perturbations.
method Refines categorical class information with soft labels from a reference network, relaxes Gaussian posterior assumption.
result Significantly outperforms benchmarked models on MNIST and CIFAR-10.
Study efficient learning of robust halfspaces with noise.
problem Learning robust halfspaces in the presence of adversarial perturbations and random label noise.
method Provides conditions for robust learnability and a simple algorithm for any ℓ_p perturbation.
result Simple computationally efficient algorithm for robust learning with random label noise.
Study reveals how high-dimensional models are vulnerable to consistent adversarial attacks.
problem Understanding the vulnerability of high-dimensional linear classifiers to adversarial attacks.
method Introducing a new error metric to quantify model vulnerability, and rigorously characterizing these metrics in asymptotic settings.
result As models become more overparameterized, their vulnerability to label-preserving perturbations increases.
MAS scores cluster size consistency from points, robust to label changes.
problem Desired uniformity in cluster sizes, stability under label perturbations.
method Mass Agreement Score (MAS) measures point-centric cluster size consistency, robust to label changes.
result MAS yields similar scores for partitions with similar bulk structure, sensitive to genuine redistribution of cluster mass.
Micro-supervised Disturbance Learning: A Perspective of Representation Probability Distributioncs.LG
New method uses small perturbations to improve representation learning from few labels.
problem Stability issues and label scarcity in representation learning.
method Introduces small-perturbation ideology on representation probability distribution models.
result Proposed models show better performance in clustering compared to baseline methods.
In machine learning, the domain adaptation problem arrives when the test (target) and the train (source) data are generated from different distributions. A key applied issue is thus the design of algorithms able to generalize on a new distribution, for which we have no label information. We focus on learning classifica…
This paper improves conformal prediction to be robust to perturbations.
problem Ensuring robustness of conformal prediction to natural and adversarial perturbations.
method Probabilistically robust conformal prediction (PRCP) and its adaptive version (aPRCP).
result aPRCP achieves better trade-offs between nominal performance and robustness.
New method uses unlabeled data to improve model robustness across different environments.
problem Learning robust models for new, unseen environments when labeled data are scarce.
method Regularizes model sensitivity to perturbations in covariate means and covariances without requiring labels.
result Empirically validated on physical and physiological datasets, demonstrating improved robustness.
The recently proposed self-ensembling methods have achieved promising results in deep semi-supervised learning, which penalize inconsistent predictions of unlabeled data under different perturbations. However, they only consider adding perturbations to each single data point, while ignoring the connections between data…
Recently, it has been shown that deep neural networks (DNN) are subject to attacks through adversarial samples. Adversarial samples are often crafted through adversarial perturbation, i.e., manipulating the original sample with minor modifications so that the DNN model labels the sample incorrectly. Given that it is al…
The study reveals how adversarial perturbations can include class features for generalization.
problem Understanding why adversarial examples deceive neural networks and transfer between networks.
method A one-hidden-layer network trained on mutually orthogonal samples.
result Adversarial perturbations, even of a few pixels, contain sufficient class features for generalization.
We tackle the PAC-Bayesian Domain Adaptation (DA) problem. This arrives when one desires to learn, from a source distribution, a good weighted majority vote (over a set of classifiers) on a different target distribution. In this context, the disagreement between classifiers is known crucial to control. In non-DA superv…
New attacks can infer model training membership using only label predictions, not confidence.
problem Inferring whether a data point was used to train a machine learning model.
method Evaluate model's predicted labels under perturbations to infer membership.
result Label-only attacks perform as well as confidence-based attacks and break defenses that rely on confidence masking.
LIME is a popular approach for explaining a black-box prediction through an interpretable model that is trained on instances in the vicinity of the predicted instance. To generate these instances, LIME randomly selects a subset of the non-zero features of the predicted instance. After that, the perturbed instances are …
Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificatescs.LG
New attack tricks certifiably robust models into mislabeling images.
problem Defeating certified defenses against adversarial examples.
method Spoofed robustness certificates and large perturbations.
result Certifiably robust models can be fooled by large perturbations.
Noise in SGD affects overparameterized models, favoring sparse solutions.
problem Understanding and mitigating implicit bias in SGD with parameter-dependent noise.
method Theoretical analysis of a quadratically-parameterized model with label noise and Gaussian noise.
result SGD with label noise recovers sparse ground-truth solutions, while SGD with Gaussian noise overfits dense solutions.
New methods protect privacy while providing accurate prediction sets.
problem Privacy-preserving conformal prediction for untrusted aggregators.
method Two LDP approaches: k-ary randomized response and binary search response.
result Finite-sample coverage guarantees and robust coverage under randomization.
Adversarial robust learning improved for transductive setting.
problem Adversarial robust learning in transductive setting.
method Simple transductive learner for bounded VC dimension classes.
result Robust error rate linear in VC dimension, adaptive to perturbation complexity.
Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and bio-informatics, where they have produced results comparable to human experts. However, th…
Mixup improves model accuracy and calibration through data transformation and random perturbation.
problem Improving model accuracy and calibration in machine learning.
method Interprets Mixup as empirical risk minimization with data transformation and random perturbation.
result Mixup induces multiple known regularization schemes that prevent overfitting and overconfident predictions.
Paper proposes a method to train robust neural networks without labeled data.
problem Training robust neural networks without class labels.
method Adversarial contrastive learning framework using unlabeled data.
result Robust Contrastive Learning (RoCL) achieves comparable robust accuracy to supervised methods and significantly improved robustness.
Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. In this paper, we propose a new algorithm, named Customized Adversarial Training (CAT), which adaptively customizes the pert…
Accelerates DNN robustness verification with target labels.
problem Improving the robustness of deep neural networks against adversarial attacks.
method Guiding robustness verification with target labels, reducing search space and using symbolic interval propagation and linear relaxation.
result Significantly improves DNN verification speed by 36X, especially when perturbation distance is reasonable.
ContrastiveVI+ models CRISPR screens with noisy guide efficiency.
problem Noisy guide efficiency in CRISPR screens.
method Generative modeling framework that disentangles perturbation-induced from shared variations.
result ContrastiveVI+ better recovers perturbation-induced variations and identifies cells without edits.
Machine learning models are vulnerable to adversarial examples. An adversary modifies the input data such that humans still assign the same label, however, machine learning models misclassify it. Previous approaches in the literature demonstrated that adversarial examples can even be generated for the remotely hosted m…
Face recognition system trained with noisy labels.
problem Label noise in training deep learning classifiers.
method Review and apply recent methods to manage noisy annotations.
result Improved performance of face recognition system with noisy labels.
Convolutional Neural Networks have been a subject of great importance over the past decade and great strides have been made in their utility for producing state of the art performance in many computer vision problems. However, the behavior of deep networks is yet to be fully understood and is still an active area of re…
Meta framework generates noise to improve multi-attack robustness.
problem Extraneous defense against single type of adversarial perturbation.
method Meta-learning framework with Meta Noise Generator (MNG).
result Significantly outperforms baselines across multiple perturbations.
This work improves structured prediction by learning the balance between signal and random noise.
problem Structured prediction with random perturbations.
method Learning the variance of randomized structured predictors to balance signal and noise.
result Learning the balance improves structured prediction effectiveness.
Recently, a variety of regularization techniques have been widely applied in deep neural networks, such as dropout, batch normalization, data augmentation, and so on. These methods mainly focus on the regularization of weight parameters to prevent overfitting effectively. In addition, label regularization techniques su…
BioBO optimizes gene perturbation design using Bayesian optimization with biological priors.
problem Efficient design of genomic perturbation experiments in drug discovery.
method Integrates Bayesian optimization with multimodal gene embeddings and enrichment analysis.
result Improves labeling efficiency by 25-40% and identifies top-performing perturbations more effectively.
Adversarial examples are malicious inputs crafted to cause a model to misclassify them. Their most common instantiation, "perturbation-based" adversarial examples introduce changes to the input that leave its true label unchanged, yet result in a different model prediction. Conversely, "invariance-based" adversarial ex…
Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, especially white-box targeted attacks. One scheme of learning attacks is to design a proper adversarial objective function that leads to the imperceptible perturbation for any test image (e.g., the Carlini-Wagner (C&W) method). Most methods address targ…
We consider the structured-output prediction problem through probabilistic approaches and generalize the "perturb-and-MAP" framework to more challenging weighted Hamming losses, which are crucial in applications. While in principle our approach is a straightforward marginalization, it requires solving many related MAP …
Study online learner attacks by manipulating labels, revealing critical thresholds.
problem Adversarial attacks on online learners, especially label manipulation.
method Control-theoretical perspective, theoretical analysis, empirical study.
result Discontinuous transition in learner's accuracy occurs at a critical threshold.
The effectiveness of Graph Convolutional Networks (GCNs) has been demonstrated in a wide range of graph-based machine learning tasks. However, the update of parameters in GCNs is only from labeled nodes, lacking the utilization of unlabeled data. In this paper, we apply Virtual Adversarial Training (VAT), an adversaria…
Inverse classification uses an induced classifier as a queryable oracle to guide test instances towards a preferred posterior class label. The result produced from the process is a set of instance-specific feature perturbations, or recommendations, that optimally improve the probability of the class label. In this work…
Adversarial examples are malicious inputs crafted to induce misclassification. Commonly studied sensitivity-based adversarial examples introduce semantically-small changes to an input that result in a different model prediction. This paper studies a complementary failure mode, invariance-based adversarial examples, tha…
Study robust online learning with adversarial perturbations.
problem Learning robust classifiers in the presence of adversarial perturbations.
method Formulated as an online learning problem, considered both realizable and agnostic learnability, defined new dimension controlling mistake/regret bounds.
result Showed new dimension controls mistake/regret bounds, generalized to multiclass hypothesis classes.