New method defends against multiple perturbation models in adversarial attacks.
problem Defending against multiple types of adversarial attacks.
method Developed a natural generalization of PGD-based procedure to incorporate multiple perturbation models.
result Trained robust models against ℓ∞, ℓ2, and ℓ1 attacks, achieving 47.0% adversarial accuracy on CIFAR10. Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small ℓ∞-noise). For other perturbations, these defenses offer no guarantees and, at times, even increase the model's vulnerability. Our aim is to understand the reasons underlying…
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.
New adversarial training methods generate multiplicative perturbations for robust DNN training.
problem Training Deep Neural Networks with adversarial examples to improve robustness.
method Proposes xAT and xVAT, generating multiplicative perturbations for robust training.
result xAT and xVAT match or outperform state-of-the-art classification accuracies and are faster.
Proposes a new video attack method that multiplies perturbation to improve model robustness.
problem Challenges existing defense methods for video recognition models against additive adversarial attacks.
method Introduces Multiplicative Adversarial Videos (MultAV) to impose perturbation by multiplication.
result Model trained against additive attacks is less robust to MultAV.
Proposes a defense method against multiple adversarial video types.
problem Lack of multi-perturbation robustness in existing defense approaches.
method Adversarial training with multiple independent BN layers and a BN selection module.
result Demonstrates stronger multi-perturbation robustness against different adversarial video types.
New quantum invariant is asymptotically multiplicative under cyclic covers.
problem Quantum invariants are not multiplicative under finite covers.
method Introduced a perturbative power series invariant of cusped hyperbolic 3-manifolds.
result The power series is asymptotically multiplicative under cyclic covers.
The paper strengthens a theorem on crossings under linear perturbations with Hausdorff measure estimates.
problem Understanding multiple-point crossings under linear perturbations.
method Establishes a transversality theorem with Hausdorff measure estimates for exceptional parameter sets.
result Explicit upper bounds on the Hausdorff dimension of the exceptional set.
DBPA assesses LLM perturbations using frequentist hypothesis testing.
problem Quantifying input perturbation impacts on LLM outputs.
method DBPA reformulates perturbation analysis as frequentist hypothesis testing, using Monte Carlo sampling for empirical null and alternative distributions.
result DBPA provides interpretable p-values and scalar effect sizes for LLM perturbations.
CausalRegNet generates accurate data for gene perturbation experiments, improving CSL methods.
problem Assessing and selecting causal structure learning methods in gene perturbation experiments.
method CausalRegNet, a multiplicative effect structural causal model, generates accurate observational and interventional data.
result CausalRegNet generates more accurate distributions and scales better than current simulation frameworks.
Simple regional perturbations maintain model transferability while reducing adversarial example distortion.
problem Comparing efficacy of regional adversarial attacks without complex methods.
method Developed a simple regional adversarial perturbation attack using cross-entropy sign.
result Localized adversarial examples require significantly less Lp norm distortion compared to non-local counterparts. Enhances GCNs' robustness to graph perturbations.
problem Vulnerability of GCNs to graph structure perturbations.
method Generates edge-dithered auxiliary graphs and uses them in an adaptive GCN.
result Significantly improved performance in SSL tasks with noisy inputs and adversarial attacks.
Enhances robustness of AT frameworks to multiple perturbations without increasing training complexity.
problem Defending against the union of multiple perturbations in adversarial training.
method SNAP technique that augments a network with shaped noise to enhance robustness.
result 14%-to-20% improvement in adversarial accuracy for ResNet-18 on CIFAR-10.
In this paper we prove that the generic singularities of mean curvature flow of closed embedded surfaces in R3 modeled by closed self-shrinkers with multiplicity has multiplicity one. Together with the previous result by Colding-Minicozzi in [CM12], we conclude that the only generic singularity of mean curva…
Study reveals class-dependent effects in perturbation-based feature attribution metrics for time series classification.
problem Varying effectiveness of perturbation-based metrics across different classes in time series models.
method Systematic empirical analysis across multiple datasets, model architectures, and perturbation strategies.
result Perturbation-based metrics show varying effectiveness across classes, with some metrics performing better for certain classes.
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.
We propose a categorical data synthesizer with a quantifiable disclosure risk. Our algorithm, named Perturbed Gibbs Sampler, can handle high-dimensional categorical data that are often intractable to represent as contingency tables. The algorithm extends a multiple imputation strategy for fully synthetic data by utiliz…
Ensemble learning that can be used to combine the predictions from multiple learners has been widely applied in pattern recognition, and has been reported to be more robust and accurate than the individual learners. This ensemble logic has recently also been more applied in feature selection. There are basically two st…
Privacy-preserving machine learning methods add randomness, leading to varying predictions.
problem Privacy-preserving machine learning methods add randomness, leading to varying predictions.
method The study analyzes three DP-ensuring algorithms: output perturbation, objective perturbation, and DP-SGD.
result The degree of predictive multiplicity rises as the level of privacy increases, and is unevenly distributed across individuals and demographic groups.
DIP-FAT improves adversarial training by diversifying perturbations.
problem Adversarial examples fool deep neural networks, leading to overfitting and poor performance.
method DIP-FAT uses random directions to diversify perturbations in adversarial training.
result DIP-FAT reduces overfitting and improves clean data accuracy.
P-OCS detects OOD samples in a low-dimensional subspace, outperforming existing methods.
problem Efficient OOD detection for deep learning models in open-world environments.
method P-OCS operates in the orthogonal complement of the principal subspace, applying a single projected perturbation.
result P-OCS achieves state-of-the-art OOD detection with negligible computational cost and without requiring model retraining.
A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we know how to optimally perturb training examples to account for test examples, we may achieve better generalization performance. However, obtaining such perturbation is not possible in standard machine learning f…
This work improves explanation quality for time series predictions by learning perturbations.
problem Explaining predictions on multivariate time series data with time dependencies.
method Learning both masks and associated perturbations to explain predictions.
result Learning perturbations significantly improves explanation quality on time series data.
We propose a novel data-driven method to learn a mixture of multiple kernels with random features that is certifiabaly robust against adverserial inputs. Specifically, we consider a distributionally robust optimization of the kernel-target alignment with respect to the distribution of training samples over a distributi…
Universal audio perturbations fool multiple classification models.
problem Creating audio adversarial perturbations that work across different models.
method Two methods: greedy iterative approach and novel penalty formulation.
result The penalty method produces more successful attacks with limited training data.
Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based attacks: The Fast Gradient Sign attack and Fast Gradient attack. First we use an …
This work introduces adversarial sparsity to measure robustness beyond adversarial accuracy.
problem Evaluating robustness to adversarial attacks beyond just accuracy.
method Adversarial sparsity, which quantifies the difficulty of finding perturbations.
result Sparsity provides valuable insights into neural networks and suggests improvements in robustness.
Latent force models are a class of hybrid models for dynamic systems, combining simple mechanistic models with flexible Gaussian process (GP) perturbations. An extension of this framework to include multiplicative interactions between the state and GP terms allows strong a priori control of the model geometry at the ex…
Motivated by the HRRT-formula for holographic entanglement entropy, we consider the following question: what are the position and the surface area of extremal surfaces in a perturbed geometry, given their anchor on the asymptotic boundary? We derive explicit expressions for the change in position and surface area, ther…
This paper solves the convergence problem for estimating MGGD parameters with a convex formulation.
problem Establishing convergence properties for estimating MGGD parameters with unknown mean and precision matrix.
method Proposes a convex formulation with well-established convergence properties for robust estimation in noisy scenarios.
result Demonstrates improved accuracy in precision and covariance matrix estimation compared to existing methods.
Improved DOA estimation with distributed sensors across multiple frequencies.
problem Sensor gain uncertainties and directional perturbations in multi-frequency scenarios.
method Distributed optimization with local coherence models and iterative exchange of information.
result Advantages in statistical and computational efficiency through parallel iterative technique.
New method generates universal adversarial perturbations across different image sources.
problem Certifying robustness of deep learning models with universal adversarial perturbations across various image sources.
method Few-shot learning approach using bilevel optimization and learning-to-optimize techniques.
result Improved attack success rate and faster performance compared to existing methods.
The paper proves that most metrics satisfy a strong version of Arnold's conjecture for Laplace eigenvalues.
problem Understanding metrics that satisfy a strong version of Arnold's conjecture for Laplace eigenvalues.
method Using geometric characterizations and perturbation theory, the paper proves the conjecture for most metrics.
result The Strong Arnold Hypothesis is satisfied for all metrics except for a set of infinite codimension.
Proposes a new method to improve deep model security against adversarial deformations.
problem Deep neural networks' resistance to adversarial attacks, especially location perturbations.
method Regularizes flow gradients to provide a tighter bound and improve model resistance.
result Models trained with flow gradient regularization show better resistance to adversarial deformations compared to input gradient regularization and adversarial training.
We consider a classifier whose test set is exposed to various perturbations that are not present in the training set. These test samples still contain enough features to map them to the same class as their unperturbed counterpart. Current architectures exhibit rapid degradation of accuracy when trained on standard data…
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 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…
Survey on Allen-Cahn equations and systems, focusing on multiplicity results and geometric interpretation.
problem Multiplicity results for Allen-Cahn equations and systems in singular perturbation regime.
method Photography method, variational-topological approach based on localized approximate solutions and barycenter maps.
result Encoding of topology into multiplicity results through variational-topological approach.
Study examines how body segments respond to random vibrations.
problem Understanding human body responses to random vibrations.
method 35 participants were tested with random noise signals. Multiple linear regression models were created to determine influential predictors of peak translational gains.
result Multiple predictors, including motion direction and body segment, significantly influence peak translational gains.
SmoothLLM defends LLMs from jailbreaking attacks by randomly perturbing inputs.
problem Adversaries can fool large language models into generating objectionable content.
method SmoothLLM randomly perturbs multiple copies of a prompt and aggregates predictions to detect adversarial inputs.
result SmoothLLM sets the state-of-the-art for robustness against various jailbreak attacks.
Inserts proximal mapping into deep networks for better regularization.
problem Effective regularization of deep learning models to handle adversarial perturbations and correlations between modalities.
method Proposes a new layer that directly produces regularized hidden layer outputs using proximal mapping.
result Outperforms state-of-the-art methods in robust temporal learning and multiview modeling.
The study examines the long-term behavior of mean curvature flows in closed 3-manifolds.
problem Understanding the long-term behavior of mean curvature flows in closed 3-manifolds.
method The approach involves constructing piecewise almost regular flows and applying perturbative arguments.
result The study constructs minimal surfaces in 3-manifolds via parabolic methods.
New method UADs improves transferability of adversarial perturbations.
problem Transferability of adversarial perturbations across different DNN architectures.
method Proposes Universal Adversarial Directions (UADs) to improve transferability.
result UADs can achieve a Nash equilibrium, indicating potential transferability.
The paper finds multiple ways a special curvature can blow up in high dimensions.
problem Finding multiple metrics with constant Q-curvature in high dimensions.
method Constructing small perturbations of standard bubbles.
result Infinitely many smooth metrics with the same constant Q-curvature and arbitrarily large energy.
A-FADMM improves FL scalability and privacy via wireless channel perturbations and interference.
problem Challenges in model training due to wireless channel randomness and interference.
method Formulated a novel constrained optimization problem and proposed A-FADMM framework.
result Proves convergence and privacy guarantees for A-FADMM under time-varying channels.
We develop several methods that allow us to compute all-loop partition functions in perturbative Chern-Simons theory with complex gauge group G_C, sometimes in multiple ways. In the background of a non-abelian irreducible flat connection, perturbative G_C invariants turn out to be interesting topological invariants, wh…
Proposes a new algorithm to estimate invariant subspaces across multilayer networks.
problem Estimating invariant subspaces across heterogeneous multiple networks.
method Bias-corrected joint spectral embedding algorithm that recursively calibrates diagonal bias and iteratively updates the subspace estimator.
result Established entrywise subspace perturbation bound and entrywise eigenvector central limit theorem for the algorithm.
DEceit constructs effective universal pixel-restricted perturbations for deep image classifiers.
problem Creating effective universal pixel-restricted perturbations for deep neural networks.
method DEceit algorithm for black-box feedback, targeting 10% of pixels in images.
result Perturbing only 10% of pixels achieves high Fooling Rate and visual similarity.