Aims to make neural networks robust to small, imperceptible perturbations.
problem Neural networks can be fooled by small, imperceptible changes.
method Proposes a Generative Adversarial Networks (GAN) framework to learn robust classifiers.
result Our method outperforms adversarial training in robustness.
AGAC uses an adversary to enhance exploration in complex tasks.
problem Sample inefficiency in complex environments, especially in tasks requiring efficient exploration.
method Integrates an adversary into the actor-critic framework to encourage innovative exploration strategies.
result AGAC leads to more exhaustive exploration and outperforms state-of-the-art methods.
DL models for MTS regression are vulnerable to adversarial attacks, posing risks in safety-critical applications.
problem Vulnerability of DL models to adversarial examples in MTS regression.
method Adversarial attack generation techniques from image classification were adapted for MTS.
result All state-of-the-art DL regression models (CNN, LSTM, GRU) are vulnerable to adversarial attacks.
Enhances exploration in hierarchical networks using mutual information.
problem Limited exploration in hierarchical Deep Q-Networks.
method Adversarial Soft Actor-Critic with mutual information optimization.
result Improves hierarchical network exploration through mutual information maximization.
The paper explores multidimensional critic output in GANs, improving convergence and diversity.
problem Underexplored in GANs literature, multidimensional critic output.
method Generalized Wasserstein GAN framework, SRVT block, maximal p-centrality discrepancy.
result High-dimensional critic output improves GAN performance in convergence and diversity.
With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input samples, called adversarial examples. Adversarial examples are imperceptible to …
AR-A3C improves A3C's robustness to noisy environments.
problem Neural networks are vulnerable to noise from unexpected sources in reinforcement learning.
method Introduced an adversarial agent to make the learning process more robust.
result AR-A3C outperforms A3C in both clean and noisy environments.
Paper improves AIRL by enhancing policy imitation and addressing reward recovery issues.
problem Inadequate policy imitation and limited transferable reward recovery in AIRL.
method Substituted built-in algorithm with SAC for policy updating and proposed PPO-AIRL + SAC hybrid framework.
result SAC improves policy imitation but hinders reward recovery; PPO-AIRL + SAC achieves satisfactory transfer effect.
Adversarial attacks pose a threat to deep neural networks, especially in safety-critical applications.
problem Adversarial attacks can misclassify deep neural networks, leading to safety issues.
method Adversarial attacks are categorized into white-box and black-box attacks based on the attacker's knowledge. They can be targeted or non-targeted.
result Adversarial attacks are effective and can transfer between different models and real-world scenarios.
This paper proposes CSADA to make DNNs cost-sensitive.
problem Over-parameterization challenges cost-sensitive classification in DNNs.
method CSADA framework using adversarial data augmentation.
result CSADA effectively minimizes overall cost and reduces critical errors.
Study adversarial attacks on cost-sensitive classifiers.
problem Safety-critical classification problems with cost-sensitive predictions.
method Used state-of-the-art adversarially-resistant neural networks and analyzed as a two-player zero-sum game.
result Introduced a new cost-sensitive attack that performs better than targeted attacks in some cases.
The paper discusses quantifying realism in generated images.
problem Designing functions to reliably distinguish realistic data from unrealistic data.
method Drawing on insights from algorithmic information theory, the paper introduces the notion of a universal critic.
result A good generative model alone is insufficient to solve the problem of realism quantification.
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.
Survey of game theory methods to secure machine learning against adversarial attacks.
problem Adversarial attacks on machine learning algorithms in cybersecurity.
method Game theory framework to make algorithms robust against adversarial data.
result Survey of state-of-the-art techniques to secure machine learning.
Deep generative models can learn to generate realistic-looking images, but many of the most effective methods are adversarial and involve a saddlepoint optimization, which requires a careful balancing of training between a generator network and a critic network. Maximum mean discrepancy networks (MMD-nets) avoid this i…
NTK neural networks are robust to adversarial attacks in nonparametric regression.
problem Adversarial robustness of neural networks in nonparametric regression.
method Gradient flow with early stopping for NTK neural networks, proving robustness in Sobolev spaces.
result NTK neural networks achieve optimal adversarial robustness rates in Sobolev spaces.
DSAC improves robustness of imitation learning.
problem Learning from few expert data and distribution shift.
method DSAC uses adversarial reward function.
result DSAC performs well on PyBullet environments.
Proposes a method to identify critical regions in neural networks using adversarial attacks.
problem Capturing uncertainty in neural networks near decision boundaries.
method Adversarial attack method to derive uncertainty from input perturbations.
result The proposed method outperforms other uncertainty methods in capturing model uncertainty.
Novel technique detects adversarial samples in face recognition models.
problem Widespread adversarial sample attacks on DNN models.
method Bi-directional correspondence inference between attributes and internal neurons to identify critical neurons.
result 94% detection accuracy for 7 different kinds of attacks with 9.91% false positives.
New defense improves numerical stability in regression networks.
problem Adversarial attacks on regression neural networks.
method Formulated a stability-inducing regularization defense.
result Defense outperforms prior approaches and improves numerical stability.
Paper tackles robustness in adversarial noise with a meta-optimizer.
problem Sensitivity to adversarial noise hinders machine learning deployment.
method Meta-optimizer learns to robustly optimize models using adversarial examples.
result Meta-optimizer transfers adversarial knowledge to new models without generating new examples.
A Bayesian framework models adversarial uncertainty for robust machine learning.
problem Vulnerability of machine learning models to adversarial attacks.
method Formal Bayesian framework that models adversarial uncertainty through a stochastic channel, articulating probabilistic assumptions.
result Explicitly modeling adversarial uncertainty leads to improved robustification strategies.
Improves RL generalization by minimizing adversarial risk.
problem Overfitting to training environments and poor generalization to unseen scenarios.
method Introduces minimax formulation and distributional framework to RL.
result Trained policy shows improved generalization to different environments.
The easiness at which adversarial instances can be generated in deep neural networks raises some fundamental questions on their functioning and concerns on their use in critical systems. In this paper, we draw a connection between over-generalization and adversaries: a possible cause of adversaries lies in models desig…
Adversarial attacks on probabilistic state-space models affect latent state and policy decisions.
problem Robust reinforcement learning under adversarial observability.
method Analyzing adversarial attacks on linear probabilistic state-space models.
result Demonstrating the influence of adversarial observations on latent state and policy decisions.
Both generative adversarial networks (GAN) in unsupervised learning and actor-critic methods in reinforcement learning (RL) have gained a reputation for being difficult to optimize. Practitioners in both fields have amassed a large number of strategies to mitigate these instabilities and improve training. Here we show …
Adversarial method finds rare catastrophic failures in safety-critical agents.
problem Evaluating safety-critical learning systems for catastrophic failures.
method Adversarial evaluation approach focusing on rare adversarial situations.
result Adversarial evaluation finds catastrophic failures and estimates failure rates faster.
Study shows prior Lipschitz continuity can improve adversarial robustness of Bayesian Neural Networks.
problem Improving adversarial robustness of Bayesian Neural Networks.
method Analysis of i.i.d., zero-mean Gaussian priors and posteriors approximated via mean-field variational inference.
result Adversarial robustness is sensitive to the prior variance.
Paper develops robust Bayesian models for linear regression under adversarial perturbations.
problem Ensuring reliable machine learning models under data perturbations.
method Formulates adversarial Bregman divergence loss, computes adversarial perturbation, introduces adversarially robust posteriors, derives generalization certificates.
result Derives first rigorous generalization certificates for adversarially robust Bayesian linear regression.
Guarantees robustness of Gaussian process classifiers against adversarial attacks.
problem Protecting machine learning classifiers from adversarial perturbations.
method Developed an adversarial bound (AB) for Gaussian process classifiers, providing a formal guarantee of robustness.
result Proves that the proposed method produces a practical, useful, and provably robust classifier.
Framework improves fairness in machine learning models using adversarial techniques.
problem Unfair decision processes in machine learning models.
method Two-step framework involving fairness optimization and evasion attacks.
result Framework significantly improves fairness metrics on tested datasets.
Deep neural networks (DNNs) are vulnerable to maliciously generated adversarial examples. These examples are intentionally designed by making imperceptible perturbations and often mislead a DNN into making an incorrect prediction. This phenomenon means that there is significant risk in applying DNNs to safety-critical …
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.
Develops robust ML systems for predictive uncertainties and adversarial examples.
problem Uncertainties and vulnerabilities in ML predictions and adversarial examples.
method Bayesian structural time series models, SG-MCMC, SVGD, Markov chain samplers, reinforcement learning.
result Improved robustness and efficiency in Bayesian inference and adversarial machine learning.
Generates multimodal safety-critical scenarios for robustness evaluation of decision-making algorithms.
problem Lack of comprehensive evaluation of neural network robustness under real-world scenarios.
method Proposes a flow-based multimodal scenario generator using weighted likelihood maximization and gradient-based sampling.
result Demonstrates improved testing efficiency and multimodal modeling capability compared to traditional methods.
MAT combines meta-learning and adversarial training to defend against universal patches.
problem Defending against universal patches that fool models in various contexts.
method Meta adversarial training (MAT) integrates meta-learning with adversarial training.
result MAT increases robustness against universal patch attacks on image classification and traffic-light detection.
This paper analyzes the limits of neural networks under adversarial attacks.
problem Understanding how neural networks perform under adversarial noise.
method Defined the adversarial VC-dimension and combined it with the VC-dimension of halfspace classifiers.
result Concluded the adversarial VC-dimension of neural networks with sign activation functions.
Survey on adversarial attacks and defenses for images, graphs, and text.
problem Adversarial examples threaten the safety of deep learning applications.
method Review of adversarial attack and defense mechanisms for images, graphs, and text.
result Systematic overview of adversarial attacks and countermeasures.
Bayesian adversaries can outsmart traditional adversarial attacks.
problem Bayesian adversaries can manipulate machine learning models through small perturbations.
method Developed a continuous-time particle system (Abram) to approximate the gradient flow of the Bayesian adversarial robustness problem.
result Abram approximates the minimizer of the Bayesian adversarial robustness problem under certain assumptions.
This paper examines various definitions of adversarial risk and their implications.
problem Quantifying the performance of classifiers under adversarial perturbations.
method Optimal transport, robust statistics, functional analysis, and game theory.
result Generalization of Strassen's theorem and new connections to Choquet capacities and game theory.
Linear classifiers can resist adversarial attacks on Gaussian data.
problem Adversarial attacks on high-dimensional data.
method Adversarial training of linear classifiers on Gaussian data.
result Linear classifiers can resist adversarial attacks on Gaussian data.
Paper improves candlestick classification model's resistance to adversarial attacks.
problem Adversarial attacks on deep learning models for candlestick classification.
method Constructs perturbed examples to enhance model robustness.
result Boosted stability of DL models for candlestick classification.
Motivated by safety-critical applications, test-time attacks on classifiers via adversarial examples has recently received a great deal of attention. However, there is a general lack of understanding on why adversarial examples arise; whether they originate due to inherent properties of data or due to lack of training …
An intriguing property of deep neural networks is their inherent vulnerability to adversarial inputs, which significantly hinders their application in security-critical domains. Most existing detection methods attempt to use carefully engineered patterns to distinguish adversarial inputs from their genuine counterparts…
Adversarial Lipschitz Regularization improves Wasserstein GANs without gradient norm penalties.
problem Training stability and sample quality issues in Wasserstein GANs.
method Explicit Lipschitz penalty using adversarial training.
result Explicit Lipschitz penalty leads to competitive performance in Wasserstein GANs.
Deep learning models are vulnerable to adversarial attacks, leading to critical errors.
problem Vulnerability of deep learning models to adversarial attacks in critical applications.
method Implemented various defenses (adversarial training, dimensionality reduction, prediction similarity) against adversarial attacks.
result Models became more robust against adversarial attacks without significant loss in accuracy.
Study robustness of split conformal prediction under adversarial attacks.
problem Ensuring distribution-free coverage guarantees in CP under adversarial conditions.
method Theoretical analysis and extensive experiments on split conformal prediction robustness.
result Prediction coverage varies with calibration-time attack strength, enabling control over coverage under adversarial tests.
The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data. Adversarial attacks in deep learning have emerged as one of the dominating security threat to a range of mission-critical deep learning systems and applications. This paper ta…