Adaptive framework generates challenging adversarial scenarios for autonomous vehicles.
problem Lack of efficient and adaptable evaluation methods for autonomous vehicles.
method Adaptive evaluation framework using ensemble models and nonparametric Bayesian clustering.
result Adversarial scenarios significantly degrade tested autonomous vehicles' performance.
Generative Adversarial Regression (GAR) learns risk scenarios robustly across policies.
problem Learning risk scenarios for conditional risk objectives.
method Generative adversarial framework for risk matching.
result GAR produces more stable and risk-preserving scenarios than baselines.
A new method for generating samples in multi-class scenarios using GANs and classifiers.
problem Generating samples for specific classes in multi-class scenarios.
method Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN) method where the generator is conditional and the classification error is backpropagated.
result The method improves sample generation for specific classes in multi-class scenarios.
S2SNets defend against adversarial attacks by interpreting perturbations as signal.
problem Fragility of deep neural networks to adversarial attacks.
method Two-stage training of S2SNets: unsupervised first, fine-tuning second, using classifier gradients.
result S2SNets achieve comparable resilience in white-box attacks and robustness in gray-box attacks.
Bayesian GAN generates diverse renewable scenarios efficiently.
problem Generating diverse and accurate renewable energy scenarios.
method Bayesian GAN, a deep neural network approach.
result Generates clusters of wind and solar scenarios with different variance and mean values.
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.
Learning theory has largely focused on two main learning scenarios. The first is the classical statistical setting where instances are drawn i.i.d. from a fixed distribution and the second scenario is the online learning, completely adversarial scenario where adversary at every time step picks the worst instance to pro…
Researchers develop PAIN to improve self-driving safety through adversarial training.
problem Overfitting and poor generalizability of neural networks in self-driving vehicles.
method PAIN combines adversarial training in CARLA simulation to generate edge cases.
result Trained self-driving vehicles are more resilient to environmental uncertainty and less prone to collisions.
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.
Bayesian methods improve adversarial machine learning robustness.
problem Improving machine learning systems' security against adversarial manipulation.
method Integrating Bayesian perspectives to relax unrealistic assumptions in game-theoretic models.
result Bayesian approach provides more robust inferences about opponent's beliefs and interests.
Generative Adversarial Network (GAN) simulates realistic multi-asset scenarios for tail risk.
problem Simulating realistic joint dynamics of multi-asset portfolios for tail risk estimation.
method Designing a GAN that preserves Value-at-Risk (VaR) and Expected Shortfall (ES) tail risk features.
result Correctly captures tail risk for a broad class of trading strategies and demonstrates strong generalization.
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.
Paper shows MoM is optimal under adversarial contamination for certain distributions.
problem Optimality of MoM under adversarial contamination.
method Upper and lower bounds for MoM's error under adversarial contamination.
result MoM is (minimax) optimal for distributions with finite variance and infinite variance with finite absolute moments.
This paper characterizes and designs loss functions for robust classification with abstention.
problem Ensuring robustness against adversarial attacks and knowing when to abstain from prediction.
method Proposes adversarial robust reject option loss and characterizes surrogates for calibration.
result Shifted Double Ramp Loss and Shifted Double Sigmoid Loss satisfy the calibration conditions.
Detects adversaries in crowdsourcing to improve accuracy.
problem Adversaries can skew results in crowdsourced classification.
method Analyzes second-order moments of annotator responses to identify and mitigate adversaries.
result The approach can identify and mitigate adversaries in crowdsourcing tasks.
This paper surveys black-box attacks on computer vision models.
problem Real-life adversarial attacks on deep learning models.
method Comprehensive comparative study of attacks and defenses.
result Significant amount of research on reliability of models.
Gradient adversarial training improves robustness and multi-task learning.
problem Improving neural network robustness and multi-task learning.
method Leverage auxiliary network to classify gradient tensors and enforce consistency with the main network.
result Gradient adversarial training enhances robustness to adversarial attacks and improves knowledge distillation.
Study on adversarial robustness in neural networks across initialization and training phases.
problem Understanding adversarial robustness in neural networks during different learning stages.
method Analyzes adversarial robustness in various scenarios of over-parameterized networks with quadratic targets and infinite samples.
result Robustness can worsen when test error improves, and vice versa, revealing new tradeoffs.
This work proposes a robust ensemble method for decision trees that resists adversarial attacks.
problem Adversarial attacks on machine learning models, especially decision trees.
method Feature partitioning to train robust ensembles and approximate certification methods.
result The proposed ensemble method can resist evasion attacks by a majority of its models.
Deep models for financial transactions are vulnerable to adversarial attacks, especially when adding transaction tokens.
problem Vulnerability of deep models to adversarial attacks on financial transaction records.
method Examine adversarial attacks and defenses on transaction records data, considering black-box attacks and adding transaction tokens.
result A few generated transactions can fool a deep-learning model, highlighting the need for robustness improvements.
Evaluates SHIELD's effectiveness against adaptive adversaries in various threat models.
problem Evaluating SHIELD's efficacy against adaptive adversaries in different threat models.
method Empirical analysis of SHIELD's robustness against adaptive attacks using Projected Gradient Descent (PGD) attacks in various threat models (white-box, gray-box).
result The targeted PGD attack success rate drops from 64.3% to 48.9% when models are trained from scratch instead of retrained.
Paper introduces TMDPs for RL in adversarial settings.
problem Adversaries interfering with reward in RL scenarios.
method TMDPs and level-k thinking scheme. result Benefits of considering adversaries in RL learning.
Develops model selection for bandits balancing adversarial and stochastic guarantees.
problem Model selection in bandit scenarios with simultaneous adversarial and stochastic high-probability regret.
method Nested policy classes, balanced candidate regret bounds, mis-specification tests.
result Best of both world guarantees in linear bandits with simultaneous adversarial and stochastic environments.
New method constrains CNN filter frequencies to improve robustness.
problem CNN bias towards low frequency components, leading to poor performance in scenario transformations.
method Frequency domain regularization by constraining filter spectra, training valid frequency range end-to-end.
result Demonstrated effectiveness in defending adversarial perturbations, reducing generalization gap, and improving transfer learning.
Anomaly detection method tackles hidden adversary actions in real-world scenarios.
problem Detecting hidden adversary actions in real-world scenarios where the defender cannot perfectly observe the attacker's actions.
method Extends existing anomaly detection models to handle continuous action spaces and game-theoretic framework. Proposes two algorithms: direct extension and learning-based approach.
result Learning-based approach produces less exploitable strategies and is scalable to higher dimensions.
FADO detects adversarial scenarios without stochastic methods.
problem Adversarial scenarios where stochastic methods are not applicable.
method Machine learning and online learning theory-based deterministic detection.
result FADO provides theoretical guarantees for detection performance.
Law responds to adversarial machine learning threats.
problem Adversarial machine learning attacks and their legal implications.
method Scenarios and legal analysis of adversarial ML attacks.
result Some attacks are more likely to result in liability.
MulDef defends neural networks against adversarial examples by combining multiple models.
problem Vulnerability of neural networks to adversarial examples.
method A general defense framework based on multiple models with robustness diversity.
result Substantially improved accuracy on adversarial examples (22-74%) while maintaining similar accuracy on legitimate examples.
We use Bayesian optimization to create efficient adversarial attacks with limited queries.
problem Creating adversarial examples with limited query access.
method Bayesian optimization for query-efficient adversarial attacks.
result Our method reduces query count by up to 80% compared to state-of-the-art methods.
One pixel attack can fool deep neural networks, showing their vulnerability.
problem Vulnerability of deep neural networks to small perturbations in input.
method Proposes a novel method using differential evolution (DE) for generating one-pixel adversarial perturbations.
result 67.97% of natural images and 16.04% of ImageNet images can be fooled by modifying just one pixel.
ARFs generate plausible counterfactuals for models, improving model understanding.
problem Creating realistic counterfactuals for model analysis.
method Adversarial Random Forests (ARFs) for generating plausible counterfactuals.
result ARFs efficiently generate plausible counterfactuals in a model-agnostic way.
Adversarial training can hurt robust accuracy in small sample size scenarios.
problem Adversarial training improves test accuracy but may degrade robustness in limited data settings.
method Analyzes high-dimensional linear classification with noiseless observations, and observes perceptible attacks on image datasets.
result Adversarial training can negatively impact robust generalization in small sample size regimes.
Study on robustness in linear regression models, focusing on adversarial perturbations.
problem Understanding and improving robustness in linear regression models to adversarial perturbations.
method Developed a two-stage adversarial learning framework that incorporates model structure information.
result Proved the consistency and developed the Bahadur representation of the adversarially robust estimator.
This paper explores the connection between adversarial and knowledge transferability.
problem Understanding the factors affecting knowledge transferability.
method Theoretical analysis and practical metrics for adversarial transferability.
result Adversarial transferability and knowledge transferability are closely related.
Adversarial autoencoder networks detect accounting anomalies in latent space.
problem Detecting fraud in accounting data using handcrafted rules that fail to generalize.
method Adversarial autoencoder neural networks to learn semantic meaningful representations.
result The learned representation improves anomaly detection and interpretability.
AMEAN tackles BTDA by learning meta-sub-targets to bridge domain gaps and misalignments.
problem Blending-target Domain Adaptation (BTDA) with multiple sub-targets that are hard to distinguish.
method AMEAN uses two adversarial processes: first to align source and mixed target domains, second to learn meta-sub-targets.
result AMEAN significantly outperforms existing DA algorithms in BTDA scenarios.
NoL approach improves adversarial robustness by modeling random noise during training.
problem Improving neural network robustness against adversarial attacks.
method Implicit generative modeling of random noise during training.
result Models trained with NoL perform better against a wide range of adversarial attacks.
Researchers create adversarial examples to deceive iris recognition systems.
problem Tackling the vulnerability of iris recognition systems to adversarial attacks.
method Developed a deep auto-encoder surrogate network to generate adversarial examples for iris recognition systems.
result Demonstrated that adversarial examples can fool iris recognition systems in both white-box and black-box settings.
This paper tackles near-optimal adversarial RL with switching costs, providing algorithms and matching lower bounds.
problem Adversarial RL with switching costs, where loss distribution can be non-stationary or adversarial.
method Developed novel switching-reduced algorithms with matching lower bounds for known and unknown transition functions.
result Achieved near-optimal performance in adversarial RL with switching costs, matching theoretical lower bounds.
Simple physical modifications can fool autonomous driving systems.
problem Vulnerability of autonomous driving models to adversarial attacks.
method Demonstrated end-to-end attacks on autonomous driving using simple physical modifications.
result Simple physical modifications can induce activation patterns similar to different scenarios used in training, fooling autonomous driving models.
This paper explores evasion attacks against Bayesian models.
problem Bayesian predictive models are vulnerable to evasion attacks.
method Developed gradient-based attacks for specific point predictions and entire posterior distributions.
result Optimal evasion attacks can be designed against Bayesian models.
Generative adversarial networks reconstruct MRI images without full data.
problem Lack of fully-sampled ground truth data for supervised MRI reconstruction.
method Generative adversarial networks for unsupervised MRI reconstruction.
result Reconstructed images show more anatomical structure than conventional methods.
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.
Cascade adversarial training improves robustness against iterative attacks.
problem Improving robustness against unknown iterative attacks.
method Cascade adversarial training, incorporating adversarial images and embedding space for low-level similarity learning.
result Enhanced robustness against iterative attacks, but decreased robustness against one-step attacks.
A new method for estimating adversarial strategies in nonlinear systems.
problem Inferring an intelligent adversarial agent's strategy in highly nonlinear systems.
method Formulated inverse cognition as a nonlinear Gaussian state-space model and developed an inverse UKF (IUKF) system.
result The estimation error of IUKF converges and closely follows the recursive Cramér-Rao lower bound.
We study the problem of allocating stocks to dark pools. We propose and analyze an optimal approach for allocations, if continuous-valued allocations are allowed. We also propose a modification for the case when only integer-valued allocations are possible. We extend the previous work on this problem to adversarial sce…
This work makes deep neural networks more resilient to adversarial attacks.
problem Making deep neural networks more resilient to adversarial attacks in real-time systems.
method Used GTSRB dataset to craft adversarial samples, then attacked a Deep Convolutional Neural Network to build a more resilient network.
result Built a more robust deep neural network that can resist adversarial attacks.
A new neural network model enhances adversarial robustness without sacrificing task performance.
problem Adversarial attacks on neural networks deployed in real-world scenarios.
method Proposes a novel neural network paradigm where each parameter is modeled as a statistical distribution with learnable parameters.
result Demonstrates highly robust performance to various adversarial attacks while maintaining task-specific performance.