RIDS reconstructs sparse gene regulatory networks from few perturbation experiments.
problem Inference of gene regulatory networks from costly perturbation experiments.
method Robust IDentification of Sparse networks (RIDS) method using sparse optimization.
result RIDS can reconstruct GRNs from a small number of experiments, achieving high performance.
Active learning reduces spin network inference complexity by 10^6-fold.
problem Difficulty in inferring direct interactions in complex networks.
method Information geometry framework to quantify inference difficulty and information gain from perturbations.
result Designed perturbations reduce sampling complexity by 10^6-fold across various network architectures.
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.
Improved algorithm speeds up generation of universal adversarial perturbations.
problem Slow generation of universal adversarial perturbations.
method Optimized algorithm based on orientation of perturbation vectors.
result Significantly faster generation of universal perturbations with higher fooling rates.
Automated tests detect interactions in unstructured data.
problem Detecting interactions between latent variables in low-dimensional systems.
method Derive two interaction tests based on pairwise interventions and integrate them into an active learning pipeline.
result Tests can identify more known biological interactions than random search and standard active learning baselines.
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.
Universal audio perturbations fool ASR systems.
problem Speech recognition systems are vulnerable to adversarial attacks.
method Developed an algorithm to create universal perturbations that fool ASR models.
result Universal perturbations can fool ASR systems across different models.
Generative models create image perturbations to fool AI models.
problem Creating adversarial examples that fool pre-trained models.
method Trainable deep neural networks for image perturbation generation.
result High fooling rates with small perturbation norms, faster than current methods.
The paper examines how gradient descent stabilizes low-rank matrix factorization in noisy conditions.
problem Stability of low-rank implicit regularization in perturbed deep matrix factorization.
method Derives spectral conditions for gradient descent to exhibit a low-rank phase in noiseless settings and analyzes perturbed dynamics.
result Gradient descent converges to a low-rank solution under perturbation, with explicit dependence on perturbation size.
Paper proposes a method to generate adversarial perturbations for black-box attacks without accessing inner states.
problem Generating adversarial perturbations for black-box attacks without accessing inner states of a DNN.
method Matrix-free generation method that requires fewer query trials.
result The proposed method successfully deceives a DNN for semantic segmentation more effectively than random noise.
Spiking neural networks maintain robust classification even with perturbed inputs.
problem Maintaining robustness of spiking neural networks under perturbed inputs.
method Extensive experiments on the XOR problem and benchmark datasets using SpikeProp algorithm.
result Classification ability of spiking neural networks is not significantly reduced by sinusoidal and Gaussian perturbations.
Enhances classification performance with small, additive perturbations.
problem Improving classification performance using small, additive perturbations.
method Proposes a perturbation generation network (PGN) based on adversarial learning to enhance classifier performance.
result Demonstrates that PGN can enhance overall classification performance without altering the target classifier network.
CAT improves robustness of neural networks by customizing perturbation levels.
problem Poor generalization of adversarial training on clean and perturbed data.
method CAT adapts perturbation level and label for each sample.
result CAT achieves better clean and robust accuracy than previous methods.
Minimal token perturbations reveal how Transformer models process information.
problem Understanding information propagation in Transformer models for interpretability.
method Study of minimal token perturbations on embedding space.
result Rare tokens cause larger shifts, and input information mixes deeper.
Novel method measures DNN sensitivity to perturbations.
problem Vulnerability of DNNs to adversarial examples.
method Perturbation manifold and influence measure.
result Demonstrated usefulness for model building tasks.
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.
SmoothFool efficiently computes smooth adversarial perturbations for deep networks.
problem Vulnerability of deep neural networks to adversarial attacks with specific statistical properties.
method SmoothFool: a general and computationally efficient framework for computing smooth adversarial perturbations.
result Smoothness significantly enhances robustness against adversarial attacks and improves transferability.
Proposes a new method to identify important input features using maximally invariant data perturbation.
problem Lack of formal mathematical definitions for feature scoring in complex machine learning models.
method Formulates the problem as linear programming to find the maximally invariant data perturbation.
result Identifies relevant parts of images effectively, distinguishing important input features.
Improved online Lasso reduces regret in sparse linear contextual bandits.
problem Sparse linear contextual bandit problem with inefficient sampling.
method Perturbed adversary approach to alleviate sampling inefficiency.
result Online Lasso achieves O ( k T log d ) \mathcal{O}(\sqrt{kT\log d}) O ( k T log d ) regret bound. New perturbative method improves stochastic gradient descent for binary weights.
problem Improving stochastic gradient descent for binary weights.
method Perturbative expansion around the mean of the sampling distribution, Taylor-corrected estimators, variance reduction techniques.
result Perturbative correction improves convergence of stochastic variational inference.
CNNs can be improved by structurally perturbing inputs.
problem Understanding and improving the behavior of deep neural networks.
method Structural perturbations to input images to improve network predictions.
result Guided perturbations can enhance prediction performance of pre-trained CNNs.
Study shows adversarial robustness and common perturbation robustness are independent.
problem Understanding the relationship between adversarial robustness and common perturbation robustness in neural networks.
method Conducted experiments to benchmark neural network robustness to common perturbations and adversarial examples.
result Adversarial robustness and common perturbation robustness are independent attributes.
New method μ P 2 μP^2 μ P 2 improves neural network training by scaling perturbations layerwise.
problem Improving neural network performance as models scale up.
method Layerwise perturbation scaling in the infinite-width limit of neural networks.
result Layerwise perturbation scaling ensures all layers are effectively perturbed in the limit.
We introduce an efficient message passing scheme for solving Constraint Satisfaction Problems (CSPs), which uses stochastic perturbation of Belief Propagation (BP) and Survey Propagation (SP) messages to bypass decimation and directly produce a single satisfying assignment. Our first CSP solver, called Perturbed Blief …
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 L p L_p L p norm distortion compared to non-local counterparts. P&C combines multiple perturbed graphs to improve influential spreader detection.
problem Ineffective algorithms are unstable to small network perturbations.
method Creates multiple perturbed graphs, applies scoring function to each, and combines results.
result P&C significantly improves influential spreader detection without extra cost.
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.
The paper learns perturbation sets from data to improve robustness in machine learning.
problem Real-world perturbations are not well characterized in adversarial defenses.
method A conditional generator defines perturbation sets over latent space, with properties for quality measured.
result Learned perturbation sets generate diverse, meaningful perturbations and improve model robustness.
SGD converges with perturbed forward-backward passes, explained by geometric amplification.
problem Analyzing convergence of SGD with perturbed forward-backward passes in composite optimization.
method Characterized propagation and amplification of perturbations, derived convergence guarantees for non-convex and PL objectives.
result Perturbations cascade through the computational graph, affecting convergence order under specific conditions.
ScieNet improves deep learning resilience to input perturbations.
problem Deep learning's poor resilience to input perturbations in real-world scenarios.
method Hybrid architecture combining SNN for contextual info extraction and DNN for classification.
result Significant improvement in accuracy on noisy and rainy images without prior training.
The paper studies the asymptotic behavior of adversarial training under ℓ ∞ \ell_\infty ℓ ∞ -perturbation.
problem Theoretical guarantees for sparsity-recovery in adversarial training.
method Investigation of the asymptotic distribution of the adversarial training estimator in generalized linear models.
result The asymptotic distribution of the adversarial training estimator under ℓ ∞ \ell_\infty ℓ ∞ -perturbation could have a positive probability mass at 0 when the true parameter is 0. Paper analyzes GCNN sensitivity to probabilistic graph perturbations.
problem Investigating how GCNNs handle probabilistic graph errors.
method Establishes error bounds and linear relationships between GSO perturbations and GCNN outputs.
result GCNNs maintain stability under graph edge perturbations if GSO errors are bounded.
Gradient noise improves privacy-protected optimization performance.
problem Improving privacy in convex optimization while maintaining utility.
method We analyze the effect of gradient perturbation on differentially private convex optimization, focusing on expected curvature.
result Gradient perturbation can achieve a significantly improved utility guarantee for differentially private convex optimization.
PEP improves deep network performance and calibration by perturbing optimal parameters.
problem Improving deep network performance and calibration.
method Parameter Ensembling by Perturbation (PEP) constructs an ensemble of parameter values as random perturbations of the optimal set, maximizing log-likelihood on validation data.
result PEP provides a small to substantial improvement in calibration and log-likelihood, and in some cases, classification accuracy.
Efficiently learns perturb-and-map models using weighted log-likelihood.
problem Structured output prediction with weighted Hamming losses.
method Generalizes perturb-and-MAP framework, uses dynamic graph cuts for MAP inference, and double stochastic gradient descent for efficient learning.
result Shows efficiency in learning log-supermodular models with weak supervision.
A new method for generating SPX and VIX risk scenarios using perturbed optimal transport.
problem Generating accurate risk estimates for SPX and VIX without full recalibration.
method A joint optimal transport calibration with perturbation methodology for sensitivities, combined with Skew Stickiness Ratio dynamics.
result The proposed method produces accurate risk estimates relative to full recalibration and is computationally faster.
This work formalizes robustness criteria for reinforcement learning actions and improves performance in perturbed environments.
problem Improving reinforcement learning policies to perform well in uncertain or adversarial action scenarios.
method Formalized two robustness criteria for reinforcement learning actions, considering adversarial actions and action perturbations. Developed algorithms for tabular and deep reinforcement learning settings.
result Action-robust reinforcement learning policies improve performance in perturbed environments and are a form of implicit regularization.
New method identifies latent variables with sparse perturbations.
problem Identifying latent variables with minimal supervision.
method Weakly supervised representation learning with sparse perturbations.
result Identification of latent variables up to specified blocks.
Semantify-NN verifies neural network robustness against semantic perturbations.
problem Verifying robustness of neural networks against semantic adversarial attacks.
method Inserting semantic perturbation layers (SP-layers) into neural networks to verify robustness.
result Semantify-NN significantly improves robustness verification performance over ℓ p \ell_p ℓ p -norm-based methods. Novel framework predicts cell responses to perturbations using GRNs.
problem Predicting cellular responses to perturbations for drug discovery and personalized therapeutics.
method Graph variational Bayesian causal inference framework with refined GRNs and robust estimator.
result Enhanced model performance and robust estimation of perturbation effects.
We find ways to make physical signals misclassified by computer vision models.
problem Vulnerability of signal classifiers to adversarial perturbations in physical signals.
method Solving PDE-constrained optimization problems to construct imperceptible perturbations.
result Effective and physically realizable adversarial perturbations can be computed for machine learning models.
FineFool attacks deep models by focusing on object contours, improving attack performance.
problem Adversarial attacks on deep learning models, especially those that focus on perturbation size and success rate.
method FineFool uses attention to focus on object contours, producing more efficient and imperceptible perturbations.
result FineFool achieves better attack performance compared to state-of-the-art attacks, including higher success rate and smaller perturbations.
Gradient descent can be very slow in escaping saddle points.
problem Gradient descent's slowness in escaping saddle points.
method Gradient descent with natural random initialization and non-pathological functions.
result Gradient descent can take exponential time to escape saddle points.
Improved neural network robustness with instance-specific perturbation margins.
problem Adversarial training fails to generalize well to unperturbed test set.
method Instance adaptive adversarial training with sample-specific perturbation margins.
result Test accuracy improves with a marginal drop in robustness.
Study on low-dimensional adversarial perturbations in classification models.
problem Understanding and quantifying the effectiveness of low-dimensional adversarial perturbations.
method Analytical lower-bounds for fooling rate, considering binary classifiers under generic regularity conditions.
result Rigorous explanation for the success of heuristic methods in generating low-dimensional adversarial perturbations.
Develops fair classifiers robust to training distribution perturbations.
problem Ensuring fairness in classifiers robust to training data perturbations.
method Formulates a min-max objective function to minimize distributionally robust training loss while maintaining fairness for perturbed distributions. Uses an iterative online learning algorithm to find a fair and robust classifier.
result Our classifier maintains fairness and accuracy for a wide range of perturbations compared to state-of-the-art fair classifiers.
Efficient adversarial training improves deep network performance.
problem Improving robustness and performance of deep neural networks.
method Perturbing intermediate layer activations during adversarial training.
result Significant improvement in classification accuracy for deep models.
PRoA assesses deep learning robustness against practical functional perturbations.
problem Inadequate practical robustness verification methods for deep learning systems.
method Probabilistic robustness assessment based on adaptive concentration.
result Statistical guarantees on probabilistic robustness against functional perturbations.