On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,922 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “Adversarial Exploration”

Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE)cs.LG

This paper improves DQN agents' robustness to adversarial perturbations.

problem Improving DQN agents' robustness to adversarial perturbations.

method Adversarial training and a novel AGE mechanism based on

ε

-greedy and Boltzmann exploration.

result AGE mechanism enhances DQN agents' robustness to adversarial perturbations.

DQN Adversarial Training Robustness Exploration ε-greedy

2019-06-03abs ↗pdf ↗

Adversarially Guided Actor-Criticcs.LG

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.

reinforcement learning actor-critic exploration adversarial sample inefficiency

2021-02-08abs ↗pdf ↗

Hierarchical Soft Actor-Critic: Adversarial Exploration via Mutual Information Optimizationcs.LG

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.

Hierarchical Deep Q-Networks Adversarial Exploration Mutual Information Soft Actor-Critic

2019-06-17abs ↗pdf ↗

SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbationscs.LG

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.

adversarial attacks smooth perturbations deep learning robustness transferability

2019-10-08abs ↗pdf ↗

Adversarial Attacks on Machine Learning Cybersecurity Defences in Industrial Control Systemscs.LG

Machine learning-based IDSs in ICS are vulnerable to adversarial attacks that can bypass them.

problem Adversarial attacks on machine learning-based IDSs in ICS can lead to undetected cyber attacks.

method Used Jacobian-based Saliency Map attack to generate adversarial samples and explored adversarial training to improve model robustness.

result Classification performance of supervised models decreased by 16-20 percentage points with adversarial samples, but improved with adversarial training.

Adversarial Machine Learning Intrusion Detection Systems Industrial Control Systems Cybersecurity Adversarial Attacks

2020-04-10abs ↗pdf ↗

Vulnerability Under Adversarial Machine Learning: Bias or Variance?cs.LG

Study explores bias-variance in adversarial machine learning.

problem Understanding adversarial machine learning's impact on bias and variance.

method Investigates bias-variance trade-offs in deep neural networks using MSE and cross-entropy.

result Derives bias-variance trade-offs for classification and regression.

adversarial machine learning bias-variance deep neural networks perturbation generalization

2020-08-01abs ↗pdf ↗

Benchmarking adversarial attacks and defenses for time-series datacs.LG

This paper benchmarks time-series adversarial defenses and attacks.

problem Adversarial attacks on time-series data.

method Detailed benchmarking of adversarial defense methods in the

L_{\infty}

threat model.

result Adversarial defenses offer robustness against both strong white-box and black-box attacks.

time-series adversarial attacks adversarial defenses L-infinity robustness

2020-08-30abs ↗pdf ↗

Uncovering the Connections Between Adversarial Transferability and Knowledge Transferabilitycs.LG

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.

transfer learning adversarial examples knowledge transferability adversarial transferability metrics

2020-06-25abs ↗pdf ↗

Exploring the Hyperparameter Landscape of Adversarial Robustnesscs.LG

Adversarial training shows promise as an approach for training models that are robust towards adversarial perturbation. In this paper, we explore some of the practical challenges of adversarial training. We present a sensitivity analysis that illustrates that the effectiveness of adversarial training hinges on the sett…

2019-05-09abs ↗pdf ↗

Exploring Memorization in Adversarial Trainingcs.LG

This paper explores memorization in adversarial training and proposes a mitigation algorithm.

problem Understanding and mitigating robust overfitting in adversarial training.

method Demonstrated the capacity of deep networks to memorize adversarial examples, analyzed convergence and generalization issues, and proposed a new mitigation algorithm.

result Identified robust overfitting as a significant drawback of adversarial training and proposed a mitigation algorithm.

memorization adversarial training robust overfitting mitigation algorithm

2021-06-03abs ↗pdf ↗

Regularized Policies are Reward Robustcs.LG

Regularized policies are robust to adversarial rewards.

problem Understanding the effects of regularization on policy exploration and robustness.

method Using Fenchel duality to derive the dual problem of the regularized RL objective, showing the optimal policy is robust to adversarial rewards.

result Regularized policies are optimal for a reinforcement learning problem under adversarial reward conditions.

Reinforcement Learning Regularization Entropy Adversarial Reward Robustness

2021-01-18abs ↗pdf ↗

Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correctioncs.LG

Paper tackles continual reinforcement learning challenges with diversity exploration and adversarial self-correction.

problem Challenges in learning new tasks sequentially due to catastrophic forgetting.

method Develops an end-to-end framework (CDAN) combining unsupervised diversity exploration and adversarial self-correction.

result Final result outperforms baseline by 18.35% in NSD and 0.61 in average reward.

continual reinforcement learning catastrophic forgetting unsupervised diversity exploration adversarial self-correction Continuous Ant Maze (CAM)

2019-06-21abs ↗pdf ↗

Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonusescs.LG

Improved exploration in adversarial MDPs via dilated bonuses.

problem Global exploration in adversarial MDPs with local-search policies.

method Dilated bonuses to facilitate global exploration.

result Improved regret bounds in various MDP settings.

Policy Optimization Reinforcement Learning Adversarial MDPs Global Exploration Dilated Bonuses

2021-07-18abs ↗pdf ↗

Dropout Induced Noise for Co-Creative GAN Systemscs.LG

Dropout improves GAN outputs by preserving input constraints.

problem Generating multiple outputs from one input.

method Using Dropout in GANs to maintain input constraints.

result Enhanced generation of diverse outputs from a single input.

Generative Adversarial Networks Dropout Latent Space Exploration Input Constraints

2019-09-10abs ↗pdf ↗

Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factorscs.LG

Most previous works usually explained adversarial examples from several specific perspectives, lacking relatively integral comprehension about this problem. In this paper, we present a systematic study on adversarial examples from three aspects: the amount of training data, task-dependent and model-specific factors. Pa…

2019-02-28abs ↗pdf ↗

Adversarial Robustness of Flow-Based Generative Modelscs.LG

This paper explores adversarial robustness of flow-based generative models.

problem Robustness of flow-based generative models to adversarial attacks.

method Theoretical and empirical analysis of adversarial robustness for simple and complex flow-based models.

result Flow-based generative models are highly sensitive to adversarial attacks, but robustness can be significantly improved using hybrid adversarial training.

adversarial robustness flow-based models generative models maximum likelihood adversarial training

2019-11-20abs ↗pdf ↗

AutoBayes: Automated Bayesian Graph Exploration for Nuisance-Robust Inferencecs.LG

AutoBayes automates Bayesian graph exploration for robust machine learning.

problem Learning representations invariant to nuisance variations in machine learning.

method Automated Bayesian inference framework exploring different graphical models.

result Significant performance improvement with nuisance-invariant machine learning pipelines.

Bayesian inference graph exploration machine learning robustness representation learning

2020-07-02abs ↗pdf ↗

Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoringcs.LG

Improved ExO method achieves near-optimal bounds in both stochastic and adversarial settings.

problem Finding optimal exploration strategies in online decision-making with limited feedback.

method Exploration by Optimization with hybrid regularizers for locally observable games.

result Achieved nearly optimal bounds of

O(\sum_{a eq a^*} k^2 m^2 \log T / Δ_a)

in stochastic and adversarial environments.

exploration by optimization hybrid regularizers partial monitoring logarithmic regret adversarial robustness

2024-02-13abs ↗pdf ↗

Playing it Safe: Adversarial Robustness with an Abstain Optioncs.LG

A new approach to make classifiers safer by allowing them to abstain from making decisions on adversarial inputs.

problem Making machine learning systems robust against adversarial attacks, especially in safety-critical applications.

method Introducing a novel objective function and a simple baseline for adversarial robustness with abstention, followed by CARL (Combined Abstention Robustness Learning) for joint classifier and abstention region learning.

result Training with CARL results in a more accurate, robust, and efficient classifier than a simple baseline.

adversarial robustness abstention machine learning security safety

2019-11-25abs ↗pdf ↗

Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?cs.LG

Simple regularization methods mimic adversarial training's robustness.

problem Expensive adversarial training for robustness.

method Label smoothing and logit squeezing.

result Achieves strong adversarial robustness without adversarial examples.

adversarial training robustness label smoothing logit squeezing simple regularization

2019-10-25abs ↗pdf ↗

Theoretical Foundations of Adversarially Robust Learningcs.LG

This thesis explores robust machine learning against adversarial examples.

problem How to create machine learning systems robust to adversarial examples.

method Theoretical exploration and development of new learning algorithms with robustness guarantees.

result Developed new learning algorithms with provable robustness guarantees.

Adversarial Robustness Machine Learning Theoretical Foundations Robustness Guarantees Learning Algorithms

2023-06-13abs ↗pdf ↗

On Adversarial Mixup Resynthesisstat.ML

In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We explore models that are capable of combining the attributes of multiple inputs such that a resynthesised output is trained to fool an adversarial discriminator for real versus synthesised da…

2019-03-07abs ↗pdf ↗

Are adversarial examples inevitable?cs.LG

A wide range of defenses have been proposed to harden neural networks against adversarial attacks. However, a pattern has emerged in which the majority of adversarial defenses are quickly broken by new attacks. Given the lack of success at generating robust defenses, we are led to ask a fundamental question: Are advers…

2018-09-06abs ↗pdf ↗

Adversarial Resilience against Clean-Label Attacks in Realizable and Noisy Settingscs.LG

Study improves resilience against adversarial clean-label attacks in real and noisy settings.

problem Ensuring accurate predictions in the presence of adversarial clean-label samples.

method Sequential learning from a stream of i.i.d. data, allowing abstention for uncertain predictions.

result Theoretical analysis and adaptations for the agnostic setting with a clean-label adversary and noise.

Adversarial Attacks Clean-Label Sequential Learning Noisy Data Agnostic Setting

2025-04-17abs ↗pdf ↗

Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Explorationcs.LG

WDAIL uses Wasserstein distance for more effective reward shaping in IL.

problem Fixed reward functions in GAIL limit performance on complex tasks.

method Introduces Wasserstein distance and PPO for improved reward shaping and stability.

result Significant performance improvement in complex MuJoCo tasks.

Wasserstein distance Adversarial imitation learning Reward shaping Proximal policy optimization Continuous control tasks

2020-06-05abs ↗pdf ↗

Delving into adversarial attacks on deep policiesstat.ML

Adversarial examples have been shown to exist for a variety of deep learning architectures. Deep reinforcement learning has shown promising results on training agent policies directly on raw inputs such as image pixels. In this paper we present a novel study into adversarial attacks on deep reinforcement learning polic…

2017-05-18abs ↗pdf ↗

Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustnesscs.LG

Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems. However, recent research on adversarial examples poses enormous challenges on the robustness of SER systems by showing the susceptibility of deep neural networks to adversarial …

2018-11-28abs ↗pdf ↗

Adversarial Robustness for Codecs.LG

Adversarial attacks found to be effective on code models.

problem Adversarial robustness of code models.

method Instantiated adversarial attacks for code, demonstrated vulnerability, and improved robustness.

result Neural models for code are vulnerable to adversarial attacks.

adversarial robustness code models machine learning deep learning adversarial attacks

2020-02-11abs ↗pdf ↗

Adversarial Security Attacks and Perturbations on Machine Learning and Deep Learning Methodscs.LG

This paper reviews adversarial attacks on ML and DL models.

problem Adversarial attacks on ML and DL models.

method Review of existing adversarial attacks and perturbations.

result Comprehensive understanding of adversarial security attacks on ML and DL.

Adversarial attacks Machine learning Deep learning Cybersecurity Security attacks

2019-07-17abs ↗pdf ↗

Trace-Norm Adversarial Examplescs.LG

New adversarial examples with structured distortion sets improve robustness and perceptibility.

problem Improving adversarial robustness and perceptibility of images.

method Exploring and constraining adversarial search with trace-norms and other norms.

result Structured adversarial perturbations allow larger distortions and control over generation.

adversarial examples trace-norm perceptibility robustness image distortion

2020-07-02abs ↗pdf ↗

Adversarial Examples in Modern Machine Learning: A Reviewcs.LG

Survey of adversarial examples in visual machine learning models.

problem Vulnerability of machine learning models to adversarial examples.

method Exploration of various adversarial attack and defense methods.

result Understanding of adversarial attack and defense mechanisms.

adversarial examples machine learning visual domain image space adversarial attacks

2019-11-13abs ↗pdf ↗

Potential adversarial samples for white-box attackscs.LG

The paper identifies potential adversarial samples near decision boundaries of neural networks.

problem Vulnerability of deep neural networks to small perturbations of inputs.

method Developed a method to explore near decision boundaries of trained classifiers to identify potential adversarial samples.

result Potential adversarial samples represent only 61% of the test data but cover more than 82% of adversarial samples produced by iFGSM and 92% of those by DeepFool on CIFAR10.

adversarial samples deep neural networks decision boundaries robustness CIFAR10

2019-12-13abs ↗pdf ↗

Improved Regret for Zeroth-Order Adversarial Bandit Convex Optimisationmath.OC

Improved regret bound for adversarial bandit convex optimisation.

problem Minimizing regret in zeroth-order adversarial bandit convex optimisation.

method Identifying an improved exploratory distribution for convex functions.

result Proved minimax regret bound of

O(d^{2.5} \sqrt{n} \log(n))

regret bandit convex optimisation adversarial exploration

2020-05-31abs ↗pdf ↗

Adversarial Examples: Attacks and Defenses for Deep Learningcs.LG

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 …

2017-12-19abs ↗pdf ↗

Exploring Adversarial Examples in Malware Detectioncs.LG

The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach impressive performance with no feature engineering effort involved, but their rob…

2018-10-18abs ↗pdf ↗

Detection of Adversarial Attacks and Characterization of Adversarial Subspacecs.LG

Paper detects adversarial attacks in sound classification models.

problem Adversarial attacks threaten data-driven models, especially in sound classification.

method Detects adversarial subspaces in unitary vector domain using chordal distance and generalized Schur decomposition.

result Regularized logistic regression detector outperforms other approaches on benchmark datasets.

adversarial attacks sound classification unitary space logistic regression Schur decomposition

2019-10-26abs ↗pdf ↗

Stochastic Linear Optimization with Adversarial Corruptioncs.LG

New algorithm for linear optimization with adaptive corruption.

problem Stochastic linear optimization under adversarial corruption.

method Algorithm uses Löwner-John's ellipsoid for exploration and divides time into epochs.

result Regret increases linearly with corruption amount.

stochastic optimization linear optimization adversarial corruption Löwner-John's ellipsoid regret analysis

2019-09-04abs ↗pdf ↗

Adversarial recovery of agent rewards from latent spaces of the limit order bookcs.LG

Adversarial RL recovers agent rewards from financial market data simulations.

problem Recovering agent rewards in volatile financial markets with unknown dynamics.

method Adversarial inverse reinforcement learning in latent space simulations.

result Adversarial RL can robustly recover agent rewards from latent space representations of real market data.

reinforcement learning inverse reinforcement learning adversarial learning financial markets latent space

2019-12-09abs ↗pdf ↗

Towards Understanding Fast Adversarial Trainingcs.LG

Paper explores fast adversarial training to improve robustness with less computation.

problem Efficiently defending against adversarial examples.

method Integrates simple self-attacks for faster training, focusing on overfitting recovery.

result Shows superior robust accuracy with reduced training time compared to strong adversarial training.

adversarial training fast adversarial training overfitting robustness computational efficiency

2020-06-04abs ↗pdf ↗

Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustnesscs.LG

Stochastic LWTA networks resist adversarial attacks while maintaining accuracy.

problem Adversarial robustness of neural networks.

method Replaced ReLU with stochastic LWTA activations, trained with Variational Bayesian and PGD.

result Stochastic LWTA networks achieve state-of-the-art robustness against adversarial attacks.

Adversarial robustness Stochastic LWTA Variational Bayesian PGD training

2021-12-05abs ↗pdf ↗

Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attackscs.CR

Study shows how to manipulate VAEs for attacks and assess their robustness.

problem Adversarial attacks on Variational Autoencoders (VAE).

method Examine modifications to VAEs and propose metrics for robustness.

result Metrics to quantify the robustness of VAEs to adversarial attacks.

Variational Autoencoders Adversarial Attacks Robustness Latent Codes Model Modifications

2021-03-10abs ↗pdf ↗

Training Augmentation with Adversarial Examples for Robust Speech Recognitioncs.CL

This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial examples augmenting the original training data. Different from conventional data augmen…

2018-06-07abs ↗pdf ↗

Virtuously Safe Reinforcement Learningcs.LG

We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the limit, and the probability of escaping a dangerous situation created by the adve…

2018-05-29abs ↗pdf ↗

Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplesstat.ML

This paper explores adversarial training limits and improves model robustness against norm-bounded perturbations.

problem Understanding and improving adversarial robustness of deep neural networks.

method Systematic study of adversarial training with various factors, including model size, activation functions, and unlabeled data.

result Training robust models that go beyond state-of-the-art results by combining larger models, Swish/SiLU activations, and model weight averaging.

adversarial training robustness norm-bounded perturbations CIFAR-10 CIFAR-100

2020-10-07abs ↗pdf ↗

MultAV: Multiplicative Adversarial Videoscs.LG

Proposes a new video attack method that multiplies perturbation to improve model robustness.

problem Challenges existing defense methods for video recognition models against additive adversarial attacks.

method Introduces Multiplicative Adversarial Videos (MultAV) to impose perturbation by multiplication.

result Model trained against additive attacks is less robust to MultAV.

adversarial machine learning video recognition multiplicative perturbation additive attacks defense methods

2020-09-17abs ↗pdf ↗

Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policycs.LG

Minimalistic attacks reveal deep RL policies' vulnerabilities with little perturbation.

problem Tackling the vulnerability of deep reinforcement learning policies to minimal perturbations.

method Three key settings: black-box policy access, fractional-state adversary, and tactically-chanced attack. Formulated adversarial attacks on six Atari games.

result Deep RL policies can be significantly fooled by minimal perturbations, even in 0.01% of the input state.

deep reinforcement learning adversarial attacks atari games policy vulnerability minimal perturbation

2019-11-10abs ↗pdf ↗

Incentivising Exploration and Recommendations for Contextual Bandits with Paymentscs.LG

Proposes a model to incentivize exploration in web platforms with payments.

problem Learning and social welfare goals of web platforms with myopic users.

method Contextual bandit model with payments to incentivize exploration.

result Achieves sublinear regret while maximizing cumulative social welfare.

contextual bandits incentivization web platforms myopic users cumulative social welfare

2020-01-22abs ↗pdf ↗

PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse Designscs.LG

PaDGAN generates diverse, high-quality designs with improved performance.

problem Lack of diversity and performance improvement in generated designs.

method Integrates Determinantal Point Processes for diversity and quality, using GAN framework.

result PaDGAN generates higher quality designs with better diversity and without mode collapse.

Generative Adversarial Networks Design Diversity Performance Improvement Diverse Designs Quality Generation

2020-02-26abs ↗pdf ↗