Protects proprietary policies from imitation learning by training adversarial policy ensembles.
problem Protecting policies from external observers cloning them.
method Introduces a reinforcement learning framework that trains an ensemble of near-optimal policies, making demonstrations useless for external observers.
result Demonstrates the existence of 'non-clonable' ensembles and provides a solution to the optimization problem.
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.
New method certifies joint adversarial robustness of model ensembles.
problem Ensuring robustness of model ensembles against adversarial attacks.
method Proposes a novel technique to certify joint robustness, building on prior work on single-model robustness certification.
result Demonstrates the effectiveness of certifying joint robustness of ensembles, improving understanding of ensemble defenses.
RH-UCRL combines pessimism and optimism for robust RL.
problem Ensuring reliable performance in real-world RL tasks with worst-case scenarios.
method RH-UCRL is a model-based RL algorithm that optimizes between an agent and an adversary, distinguishing between epistemic and aleatoric uncertainty.
result RH-UCRL achieves near-optimal sample complexity guarantees and outperforms other robust RL algorithms in adversarial environments.
Ensemble of diverse CNNs detects and mitigates adversarial attacks.
problem Detecting and defending against adversarial attacks.
method An ensemble of specialized CNNs with a voting mechanism.
result Significant reduction in adversarial attack risk rate.
The paper analyzes and minimizes transferability of adversarial attacks between models in an ensemble.
problem Adversarial attacks can transfer between models, posing security risks.
method Introduces a gradient-based measure to assess and reduce transferability, and uses it during training to increase robustness.
result Demonstrates that the gradient-based measure can be used to increase an ensemble's robustness to adversarial attacks.
New algorithms reduce dynamic regret in online MDPs with changing losses.
problem Online MDPs with adversarial loss changes and known transitions.
method Dynamic regret measure, novel ensemble algorithms for three models.
result Provably optimal dynamic regret bounds for episodic SSP, improved bounds for predictable environments.
Proposes SWA for adversarial training to improve model robustness.
problem Overfitting in adversarial training due to insufficient sample complexity.
method Adversarial training with Stochastic Weight Average (SWA).
result Improves model robustness on CIFAR-10, CIFAR-100, and SVHN datasets.
DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.
problem Diverse adversarial vulnerabilities for robust ensemble models.
method Isolates and diversifies adversarial vulnerabilities through distillation and training.
result Achieves higher robustness against transfer attacks compared to previous methods.
This work improves adversarial robustness by boosting model ensembles with margin maximization.
problem Single models are insufficient for defending against adversarial attacks.
method Margin-boosting approach to learn ensembles with maximum margin.
result Our algorithm outperforms existing ensembling techniques and large models trained end-to-end.
A novel approach uses an ensemble of Gaussian processes for robust and adaptive reinforcement learning.
problem Adaptive reinforcement learning in large or continuous state spaces.
method Online scalable (OS) approach with a weighted ensemble of Gaussian processes.
result The ensemble approach improves performance in adversarial settings.
New method tests tree models without causing computational pressure.
problem Incompatibility of adversarial robustness testing with tree ensembles.
method Smooths tree ensembles with sigmoid functions and uses gradient descent.
result Successfully reveals adversarial vulnerability of tree ensemble models.
This work studies adversarial transferability and proposes ensemble methods to improve robustness.
problem Adversarial transferability in neural networks and its implications for robustness.
method Investigates the effect of various factors on adversarial transferability and proposes ensemble attack methods.
result Transferability is significantly hampered by input quantization and architectural mismatch, but not by initialization.
Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks. Many efforts have been devoted to enhancing the robustness of individual networks and then constructing a straightforward ensemble…
Ensemble learning is a very prevalent method employed in machine learning. The relative success of ensemble methods is attributed to their ability to tackle a wide range of instances and complex problems that require different low-level approaches. However, ensemble methods are relatively less popular in reinforcement …
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.
New adversarial training enhances malware detectors against various attacks.
problem Vulnerability of malware detectors to evasion attacks.
method Proposes a mixture of attacks and adversarial training to improve deep neural networks.
result Significantly enhances robustness of deep neural networks against a wide range of attacks.
Deep Neural Networks are vulnerable to adversarial attacks even in settings where the attacker has no direct access to the model being attacked. Such attacks usually rely on the principle of transferability, whereby an attack crafted on a surrogate model tends to transfer to the target model. We show that an ensemble o…
SUNRISE improves off-policy RL algorithms by integrating ensemble methods.
problem Stability and exploration issues in off-policy RL algorithms.
method SUNRISE combines ensemble-based weighted Bellman backups and upper-confidence bounds for efficient exploration.
result SUNRISE improves the performance of off-policy RL algorithms across various domains.
Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs…
Deep learning has become the state of the art approach in many machine learning problems such as classification. It has recently been shown that deep learning is highly vulnerable to adversarial perturbations. Taking the camera systems of self-driving cars as an example, small adversarial perturbations can cause the sy…
POETS optimizes LLMs by combining policy ensembles and KL regularization.
problem Balancing exploration and exploitation in decision-making and optimization.
method POETS uses policy ensembles and KL regularization to optimize LLMs efficiently.
result POETS achieves state-of-the-art sample efficiency across various domains.
New method reduces bias in NLI models using ensemble adversarial training.
problem Spurious correlations between hypotheses and entailment classes in NLI datasets.
method Adversarial training with an ensemble of classifiers to reduce bias in sentence representations.
result Ensemble adversarial training produces more robust NLI models, outperforming previous methods.
Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN model to misclassify. In this paper, we present a cross-layer strategic ensemble fra…
Paper proposes an ensemble of attacks to evaluate adversarial robustness more reliably.
problem Insufficient evaluation of adversarial defenses leads to incorrect robustness assessments.
method Developed two extensions of PGD-attack and combined them with two complementary attacks.
result Identified several broken defenses with lower robust test accuracy than reported.
Study on adversarial training's impact on deep neural reinforcement learning policies.
problem Vulnerability of deep neural reinforcement learning policies to imperceptible adversarial perturbations.
method Two parallel approaches: Fourier spectrum analysis and feature sensitivity measurement.
result Adversarially trained policies are more sensitive to low frequency perturbations.
LOTOS improves ensemble robustness by promoting orthogonal transformations.
problem Transferability of adversarial examples threatens robustness of classification models.
method LOTOS promotes orthogonality among sub-spaces of transformations in ensemble models.
result LOTOS increases robust accuracy of ensembles by 6 percentage points against black-box attacks.
XEnsemble improves DNN robustness against adversarial and out-of-distribution inputs.
problem Protecting DNN models from adversarial and out-of-distribution inputs.
method Diverse input denoising verifiers and disagreement-diversity ensemble learning.
result XEnsemble achieves high defense and detection success rates.
Strong theoretical guarantees of robustness can be given for ensembles of classifiers generated by input randomization. Specifically, an ℓ2 bounded adversary cannot alter the ensemble prediction generated by an additive isotropic Gaussian noise, where the radius for the adversary depends on both the variance of t…
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.
Deep neural networks are vulnerable to adversarial attacks.
Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another agent's observations. This might lead one to wonder: is it possible to attack an R…
Gray-box attack improves on white-box methods for trading agents.
problem Robustness of Deep RL trading agents against adversarial attacks.
method Hybrid Deep Neural Network policy for gray-box adversarial attack.
result Adversary can reduce trading agent's reward by 214.17%.
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.
AEA dynamically aggregates ensemble targets for actor-critic learning.
problem Static ensemble aggregation methods struggle with overestimation bias and variance.
method Adaptive Ensemble Aggregation (AEA) dynamically constructs ensemble-based targets.
result AEA converges to optimal variance reduction and maximal Fisher information.
Optimizes biomolecular simulations by ranking adaptive sampling policies.
problem Efficiently sampling biomolecular systems to capture complex dynamical behaviors.
method Metric-driven ranking of adaptive sampling policies to identify the optimal policy for each round.
result Different adaptive sampling policies lead to faster convergence and improved sampling performance.
Recent advances show that deep neural networks are not robust to deliberately crafted adversarial examples which many are generated by adding human imperceptible perturbation to clear input. Consider l2 norms attacks, Project Gradient Descent (PGD) and the Carlini and Wagner (C\&W) attacks are the two main methods, …
The paper improves QD policy ensembles using distribution ratio estimators.
problem Training diverse and high-quality reinforcement learning agents.
method Using Stein variational gradient descent and distribution ratio estimators.
result The method generates diverse and high-quality reinforcement learning agents.
A new method removes policy optimization in adversarial imitation learning.
problem Adversarial imitation learning's delicate alternated optimization.
method Explicitly condition discriminator on two policies, solving generator's optimization problem directly.
result Simpler approach competitive to prevalent methods.
Adversarial attacks can manipulate deep trading policies, compromising their performance.
problem Adversarial attacks can compromise deep reinforcement learning trading policies.
method Developed a threat model and proposed two attack techniques.
result Demonstrated the effectiveness of adversarial attacks against DQN trading agents.
Despite the considerable success of convolutional neural networks in a broad array of domains, recent research has shown these to be vulnerable to small adversarial perturbations, commonly known as adversarial examples. Moreover, such examples have shown to be remarkably portable, or transferable, from one model to ano…
This study evaluates the robustness of transformation-based ensemble defense against evasion attacks.
problem Understanding the reasons behind the robustness improvement in transformation-based ensemble defense.
method Designing two adaptive attacks to evaluate transformation-based ensemble defense, conducting experiments to analyze robustness.
result The robustness improvement is mainly from irreversible transformations rather than the ensemble of models.
New approach optimizes policies in adversarial MDPs using adversarial learning.
problem Optimizing policies in adversarial Markov decision processes.
method Adversarial learning on advantage functions, extending previous reductions.
result Stronger regret criteria and performance guarantees for policy optimization.
A new method aggregates generative classifiers to resist adversarial attacks.
problem Adversarial attacks on deep neural networks.
method Rank-aggregating ensemble of generative classifiers trained on intermediate layer responses.
result The ensemble of generative classifiers shows robustness to adversarial attacks.
Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted using fast single-step methods that maximize a linear approximation of the model'…
Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we show adversarial attacks are also effective when targeting neural …
Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic performance as model-free methods. We propose Model-Based Meta-Policy-Optimization…
New method handles uncertainty in adversarial attacks using ensemble noise simulation.
problem Uncertainty in adversarial attacks on neural networks.
method Simulates attacker's noisy perturbation using various gradient-based attack algorithms and a pre-processing Denoising Autoencoder (DAE) defense.
result Significant improvements in post-attack accuracy with the proposed ensemble-trained defense.