Improves deep learning robustness by considering task and model.
problem Adversarial attacks on deep learning systems.
method Binary and interval label encoding strategy to redefine classification tasks and design corresponding loss functions.
result Our method enhances robustness without sacrificing accuracy.
Proposes model-based robust deep learning to handle natural variation in data.
problem Deep learning's fragility to natural variation in data.
method Develops model-based robust training algorithms using deep generative models to learn natural variation.
result Deep neural networks trained with model-based algorithms outperform standard and norm-bounded robust algorithms.
The study improves deep learning models for safer autonomous vehicles.
problem Robustness of deep neural network models in autonomous driving.
method Analyzes and proposes solutions for deep learning model robustness.
result Enhanced deep learning models for safer autonomous vehicles.
Deep RL policies are vulnerable to adversarial perturbations, but vanilla training yields more robust policies.
problem Vulnerability of deep reinforcement learning policies to adversarial perturbations.
method Analysis of deep reinforcement learning policy landscape and comparison of vanilla vs. adversarial training.
result Vanilla training yields more robust policies compared to adversarial training.
New metric learning improves deep networks' robustness to adversarial attacks.
problem Deep networks' fragility to adversarial attacks.
method Metric learning to regularize representation space under attack.
result Improvement of robustness accuracy by up to 4% and detection efficiency by up to 6%.
The paper proves deep learning can be robust with certain loss functions.
problem The robustness of deep learning models under flawed data.
method Empirical-risk minimization with unbounded, Lipschitz-continuous loss functions.
result These loss functions provide efficient prediction under minimal data assumptions.
Reprogram deep models to resist adversarial attacks without changing parameters.
problem Improving deep learning models' robustness against adversarial and noisy inputs.
method Proposes a non-linear robust pattern matching technique and three reprogramming paradigms.
result Demonstrates effective reprogramming of deep models for robustness without altering parameters.
Certifiable defense method improves robustness of deep learning interpretation.
problem Vulnerability of gradient-based saliency maps to adversarial attacks.
method Sparsified SmoothGrad method, extending certifiably robust smooth classifier bounds.
result Sparsified SmoothGrad method is certifiably robust against adversarial perturbations.
Deep RL for portfolio management shows poor robustness.
problem Robustness of Deep RL algorithms in online portfolio management.
method Proposed a training and evaluation process for assessing DRL algorithms.
result Most Deep RL algorithms are not robust, generalizing poorly and degrading quickly.
Robust optimization improves deep learning feature representations.
problem Deep learning feature representations lack versatility and high-level encoding.
method Robust optimization as a prior for feature learning.
result Robust models learn approximately invertible, salient feature representations.
RADIAL-RL improves deep RL agents' robustness against adversarial attacks.
problem Vulnerability of deep reinforcement learning agents to small adversarial perturbations.
method RADIAL-RL, a principled framework for training robust reinforcement learning agents.
result RADIAL-RL-trained agents consistently outperform prior methods in robustness tests.
RS-DQN protects RL agents from adversarial attacks.
problem Adversarial attacks can disrupt deep RL training and evaluation.
method Online robustness training with RS-DQN combining state-of-the-art adversarial and provably robust training.
result RS-DQN makes RL agents resilient to strong attacks.
New metric measures deep learning robustness to noise.
problem Deep learning models are vulnerable to noise.
method Formal definition of robustness as localized Lipschitz constant.
result New metric evaluated on competitive vision datasets.
Paper introduces uncertainty injection for deep learning robust optimization.
problem Uncertainty in input data affects deep learning model performance in optimization problems.
method Uncertainty injection scheme for training deep learning models to produce robust solutions.
result Proposed scheme improves robustness of solutions in wireless communications applications.
New model improves deep learning robustness against adversarial attacks.
problem Improving adversarial robustness of deep learning models.
method Local competition principle, LWTA nonlinearities, Bayesian non-parametrics.
result The new model achieves high robustness to adversarial perturbations on MNIST and CIFAR10 datasets.
Enhances deep learning models to resist adversarial attacks.
problem Protecting deep learning models from adversarial examples.
method Combines two mechanisms: increased robustness at the cost of accuracy and improved accuracy without robustness guarantee.
result Combining mechanisms provides robustness against adversarial examples while maintaining accuracy.
DSCF-Net learns deep features for clustering with robustness and locality preservation.
problem Unsupervised deep representation learning for clustering.
method Integrates robust deep concept factorization, deep self-expressive representation, and adaptive locality preserving feature learning.
result Delivers state-of-the-art performance on public databases.
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.
Paper tackles robust deep learning from weakly dependent data with unbounded loss and input.
problem Tackles robust deep learning from weakly dependent data with unbounded loss and input.
method Establishes non-asymptotic bounds for expected excess risk under strong mixing and ψ-weak dependence assumptions. result Derives a relationship between bounds and r, and shows convergence rate close to i.i.d. results for r=∞. Deep Lagrangian Networks learn physics for robust control with fewer samples.
problem Learning physics models for model-based control requires robust extrapolation from limited samples.
method Imposing Lagrangian Mechanics on a deep network structure (DeLaN).
result DeLaN outperforms previous methods at learning speed and robust extrapolation.
Paper improves deep learning models for limit order book data.
problem Deep learning models' performance depends on robust input data representation.
method Identified and modified flaws in existing representations.
result Proposed modifications lead to state-of-the-art performance.
This paper improves loss functions for deep learning with noisy labels.
problem Training deep neural networks with noisy labels.
method The paper introduces a normalization technique to make any loss function robust to noisy labels and proposes a framework called Active Passive Loss (APL) to combine robust loss functions.
result The proposed APL framework consistently outperforms state-of-the-art methods, especially under high noise rates.
Proposes a deep learning method for robust ordinal regression under label noise.
problem Label noise in real-world data constrains ordinal regression algorithms.
method Develops a deep learning approach that is robust to label noise and rank consistent.
result Demonstrates robustness to label noise and rank consistency on real data.
Proposes a new objective function to learn robust deep features.
problem Learning robust deep representations of noisy or unavailable features.
method Maximizes mutual information of all subsets of features relative to supervising signal.
result Surrogate objective function encourages non-redundant and conditionally independent features.
This work improves deep reinforcement learning robustness to adversarial state uncertainty.
problem Robustness of deep reinforcement learning to adversarial state uncertainty.
method Certified adversarial robustness techniques are applied to deep reinforcement learning algorithms to compute guaranteed lower bounds on state-action values.
result The approach increases robustness to noise and adversaries in pedestrian collision avoidance and classic control tasks.
New method speeds up training of deep networks robust to adversarial attacks.
problem Deep networks are sensitive to adversarial perturbations, compromising security and interpretability.
method Fast adversarial training using Euclidean norm approximation and distributed computing.
result Robust feature representations and reduced training time achieved.
This paper analyzes generalization issues in deep reinforcement learning.
problem Understanding and improving generalization capabilities of deep reinforcement learning policies.
method Formalizing and categorizing solutions to address overfitting in deep reinforcement learning.
result A comprehensive analysis of generalization challenges and solutions in deep reinforcement learning.
New deep learning models inspired by fuzzy logic are more robust to adversarial attacks.
problem Flawed generalization in deep neural networks leading to adversarial examples.
method Inspired by fuzzy logic, new architectures combining alternative design elements.
result New models are more robust to adversarial examples and noise.
GeFs use deep generative models to enhance prediction robustness and uncertainty.
problem Lack of principled methods to manipulate uncertainty in decision trees and random forests.
method Exploits Generative Forests (GeFs), a deep probabilistic model that extends Random Forests to represent full joint distributions.
result GeFs are uncertainty-aware classifiers capable of measuring robustness and detecting out-of-distribution samples.
New measure assesses deep neural networks' robustness to adversarial attacks.
problem Deep learning's fragility to adversarial attacks limits its adoption in mission-critical applications.
method Introduces residual error as a new performance measure for assessing adversarial robustness.
result Demonstrates effectiveness of residual error in assessing robustness of deep neural networks.
Paper benchmarks DRL policies' resilience to state transitions.
problem Measuring DRL policies' resilience to state perturbations.
method Disentangled representation learning and RL-based techniques.
result Demonstrated feasibility of resilience benchmarking in DQN, A2C, and PPO2.
New method improves deep learning by sampling worst-performing data.
problem Overfitting and poor generalization in deep learning.
method Distributional robust optimization to modify sample contributions.
result Faster convergence and higher accuracy in different scenarios.
Study evaluates deep learning methods for dermatology, finding they perform poorly under non-ideal conditions.
problem Lack of robustness of deep learning methods in dermatology under real-world conditions.
method Simulated non-ideal conditions on user-submitted dermatology images.
result Deep learning methods show significant drop in accuracy and prediction changes under non-ideal conditions.
New global adversarial attacks improve DNN robustness assessment.
problem Vulnerability of deep neural networks to adversarial attacks.
method Proposed global adversarial example pairs and attack methods.
result DNNs hardened with local adversarial training are vulnerable to global attacks.
New activation improves deep learning accuracy and robustness.
problem Improving accuracy and robustness of deep neural nets with limited data.
method Replaces softmax with graph Laplacian-based interpolating function.
result Significantly improves natural and robust accuracy.
Robust deep neural networks estimate multi-dimensional functional data robustly.
problem Estimating location function from multi-dimensional functional data robustly.
method Deep neural networks with ReLU activation, robust to outliers and model misspecification.
result Uniform convergence rates for robust deep neural network estimators.
Study evaluates adversarial training for deep learning IDSs against various attacks.
problem Evasion attacks against deep learning-based IDSs.
method Investigated adversarial training using min-max approach on CNN and RNN.
result Adversarial training improves robustness against five attack methods.
The question why deep learning algorithms generalize so well has attracted increasing research interest. However, most of the well-established approaches, such as hypothesis capacity, stability or sparseness, have not provided complete explanations (Zhang et al., 2016; Kawaguchi et al., 2017). In this work, we focus on…
New methods show robustness and accuracy can coexist.
problem Inevitability of robustness-accuracy tradeoff in deep learning.
method Prove robustness and accuracy achievable through locally Lipschitz functions; explore combining dropout with robust training methods.
result Achieving robustness and accuracy requires methods imposing local Lipschitzness and deep learning generalization techniques.
URSABench benchmarks Bayesian methods for deep learning models.
problem Scalability issues in Bayesian inference for deep learning.
method Open-source benchmark suite for assessing approximate Bayesian inference methods.
result Initial results show promise for addressing uncertainty and robustness in deep learning.
Improves natural accuracy of deep learning models by combining robust predictions and features.
problem Maintaining natural accuracy while resisting adversarial attacks.
method Ensemble methods combining robust and standard models.
result Optimized natural accuracy through ensemble of robust models.
A new algorithm for deep Q-learning with robustness to state transition uncertainty.
problem Model uncertainty in state transitions for non-tabular, continuous state spaces.
method Distributionally robust approach using worst-case transition ball and dualized Bellman operator with Sinkhorn distance.
result Optimal policy found through solving non-linear Bellman equation with neural network parameterization.
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.
New deep learning methods improve solving FBSDEs without losing stability.
problem Solving high-dimensional nonlinear FBSDEs using classical methods is computationally infeasible.
method Inspired by deep learning, propose using deep learning architectures for FBSDEs and multilevel discretization.
result Multilevel discretization improves solution times by an order of magnitude.
Study explores loss design for decision trees to improve robustness against noisy labels.
problem Improving decision tree robustness to noisy labels.
method Investigated loss correction and symmetric losses, found ineffective.
result Other loss design directions need exploration for robust decision trees.
Study improves robustness of deep fusion models against single source noise.
problem Ensuring robustness of deep fusion models against noise added to a single input source.
method Proposed two approaches: a carefully designed loss function and a convolutional fusion layer.
result Deep fusion models become robust against noise applied to a single source, preserving performance on clean data.
New approach improves deep learning robustness in medical imaging.
problem Deep learning models are vulnerable to adversarial examples in medical imaging.
method Propose a min-max learning scheme to generate adversarial examples and filter them out.
result Proposed method significantly improves robustness of deep learning models in medical imaging.
Deep models maximize minimum margin for high accuracy but decrease average margin, leading to poor robustness.
problem Inadequate balance between accuracy and robustness in deep model training.
method Analyzed the training process of deep models and proposed a new regularizer to promote average margin.
result Demonstrated an intrinsic trade-off between accuracy and robustness, and proposed a regularizer to improve robustness.