Proposes a new adversarial model to avoid accuracy vs. adversarial accuracy tradeoff.
problem Inherent tradeoff between accuracy and adversarial accuracy in existing adversarial robustness definitions.
method Introduces Voronoi-epsilon adversary that balances perturbation constraints.
result Voronoi-epsilon adversary avoids accuracy vs. adversarial accuracy tradeoff even with large ε. The paper analyzes adversarial training effects on classification accuracy.
problem Understanding adversarial training's impact on standard and robust accuracy.
method Derived precise statistical analysis for binary classification problems with Gaussian data.
result Theoretical explanation of standard and robust accuracy trends for adversarial training.
Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations and achieve high standard test accuracy. However, this is contrary to the stand…
This work introduces adversarial sparsity to measure robustness beyond adversarial accuracy.
problem Evaluating robustness to adversarial attacks beyond just accuracy.
method Adversarial sparsity, which quantifies the difficulty of finding perturbations.
result Sparsity provides valuable insights into neural networks and suggests improvements in robustness.
Adversarial training can lead to unfair accuracy disparities between different groups.
problem Adversarial training algorithms introduce unfair accuracy disparities between different groups of data.
method Propose a Fair-Robust-Learning (FRL) framework to mitigate unfairness in adversarial defenses.
result Empirical and theoretical validation of FRL's effectiveness in mitigating unfairness.
Paper shows adversarial training can be fooled by new type of noise.
problem Adversarial training can be fooled by new types of noise.
method Designing ADVIN, a new type of inducing noise.
result ADVIN can degrade adversarial training robustness by 99.9%.
In this paper, we develop improved techniques for defending against adversarial examples at scale. First, we implement the state of the art version of adversarial training at unprecedented scale on ImageNet and investigate whether it remains effective in this setting - an important open scientific question (Athalye et …
New trade-off found between accuracy and adversarial robustness in regression.
problem Finding a balance between accuracy and robustness in regression models.
method Deriving a fundamental trade-off between standard and adversarial risk in regression with polynomial ridge functions.
result A necessary condition for achieving adversarial robustness without significant accuracy loss.
The paper studies adversarial training for linear regression models.
problem Understanding the tradeoffs between robust and standard accuracy in adversarial training.
method Characterizes the fundamental tradeoff and specific adversarial training approach for linear regression with Gaussian features.
result Precise characterization of the standard and robust accuracy tradeoff in high-dimensional settings.
Adversarial attacks add perturbations to the input features with the intent of changing the classification produced by a machine learning system. Small perturbations can yield adversarial examples which are misclassified despite being virtually indistinguishable from the unperturbed input. Classifiers trained with stan…
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.
Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the most popular robust training method in the literature, adversarial training: Advers…
Tricks adversarial attacks to target specific classes, improving classifier accuracy.
problem Recent adversarial defense approaches have failed to protect classifiers from untargeted attacks.
method Target Training defense tricks untargeted attacks into targeted attacks on designated classes, then derives the real class.
result 86.2% accuracy for CW-L2 (confidence=0) in CIFAR10, outperforming unsecured classifiers.
Adversarial perturbations fool deepfake detectors with high accuracy.
problem Improving deepfake detection accuracy against adversarial attacks.
method Used adversarial perturbations and two defenses: Lipschitz regularization and Deep Image Prior (DIP).
result Deepfake detectors achieved 27% accuracy on perturbed images, compared to 95% on unperturbed.
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.
Paper explores tradeoff between standard and robust accuracy for latent models.
problem Tradeoff between standard accuracy and robust accuracy in adversarial training.
method Revisits adversarial training for latent models, considering Gaussian mixture and generalized linear models.
result Low-dimensional manifold structure mitigates the tradeoff between standard and robust accuracy.
In adversarial attacks to machine-learning classifiers, small perturbations are added to input that is correctly classified. The perturbations yield adversarial examples, which are virtually indistinguishable from the unperturbed input, and yet are misclassified. In standard neural networks used for deep learning, atta…
Modern machine learning models with very high accuracy have been shown to be vulnerable to small, adversarially chosen perturbations of the input. Given black-box access to a high-accuracy classifier f, we show how to construct a new classifier g that has high accuracy and is also robust to adversarial ℓ2-bou…
The paper examines how adversarial robustness affects accuracy disparity across different classes.
problem Understanding the impact of adversarial robustness on accuracy disparity across different classes.
method Linear classifiers under a Gaussian mixture model, decomposing the impact into inherent and imbalance effects.
result Adversarial robustness consistently degrades standard accuracy in balanced classes, but the class imbalance ratio plays a different role in accuracy disparity.
SAT improves adversarial training by smoothing the loss landscape through curriculum learning.
problem Adversarial training sacrifices clean accuracy for robustness and suffers from large generalization error.
method SAT uses curriculum learning to smooth the adversarial loss landscape, improving both clean and robust accuracy.
result SAT models improve clean and robust accuracy significantly compared to adversarial training and other baselines.
This work benchmarks and theorizes robust NAS under adversarial training.
problem Lack of benchmark evaluations and theoretical guarantees for robust NAS architectures under adversarial training.
method Released a comprehensive data set and established a generalization theory using the neural tangent kernel.
result Established a generalization theory for robust NAS architectures under adversarial training.
New defense method inspired by encryption improves visual classification accuracy.
problem Conventional defenses reduce accuracy and are defeated by obfuscated gradients.
method Block-wise pixel shuffling with secret key for training and test images.
result Achieves high accuracy (91.55%) on clean images and (89.66%) on adversarial examples.
Today's state-of-the-art image classifiers fail to correctly classify carefully manipulated adversarial images. In this work, we develop a new, localized adversarial attack that generates adversarial examples by imperceptibly altering the backgrounds of normal images. We first use this attack to highlight the unnecessa…
Improves authorship attribution accuracy and robustness against adversarial attacks.
problem Vulnerability of authorship attribution approaches to adversarial attacks.
method Formulated a relational adversary threat model and presented a novel learning framework, normalize-and-predict (N&P).
result Improves accuracy on adversarial inputs by up to 70% and robust accuracy by 45%.
Adversarial robustness has become an important research topic given empirical demonstrations on the lack of robustness of deep neural networks. Unfortunately, recent theoretical results suggest that adversarial training induces a strict tradeoff between classification accuracy and adversarial robustness. In this paper,…
Machine learning models, especially neural network (NN) classifiers, are widely used in many applications including natural language processing, computer vision and cybersecurity. They provide high accuracy under the assumption of attack-free scenarios. However, this assumption has been defied by the introduction of ad…
Adversarial examples are perturbed inputs that are designed (from a deep learning network's (DLN) parameter gradients) to mislead the DLN during test time. Intuitively, constraining the dimensionality of inputs or parameters of a network reduces the 'space' in which adversarial examples exist. Guided by this intuition,…
Neural Network classifiers have been used successfully in a wide range of applications. However, their underlying assumption of attack free environment has been defied by adversarial examples. Researchers tried to develop defenses; however, existing approaches are still far from providing effective solutions to this ev…
This paper proposes BAT to balance accuracy and robustness in adversarial training.
problem Balancing accuracy and robustness in adversarial training models.
method Blind adversarial training (BAT) uses a cutoff-scale strategy to adaptively estimate a nonuniform budget for AEs.
result BAT improves the overall robustness of adversarial training models.
Adversarial perturbations dramatically decrease the accuracy of state-of-the-art image classifiers. In this paper, we propose and analyze a simple and computationally efficient defense strategy: inject random Gaussian noise, discretize each pixel, and then feed the result into any pre-trained classifier. Theoretically,…
SPLASH units improve deep neural network accuracy and adversarial robustness.
problem Improving deep neural network accuracy and adversarial robustness.
method SPLASH units are learnable activation functions with specific properties that enhance both accuracy and robustness.
result SPLASH units significantly increase adversarial robustness of deep neural networks.
SONet stabilizes ODE networks for robustness without adversarial training.
problem Improving adversarial robustness of neural networks without sacrificing natural accuracy.
method SONet uses skew-symmetric ODE blocks and DOPRI5 solver for robustness.
result SONet achieves comparable robustness to adversarial defense methods without trade-off.
While adversarial training can improve robust accuracy (against an adversary), it sometimes hurts standard accuracy (when there is no adversary). Previous work has studied this tradeoff between standard and robust accuracy, but only in the setting where no predictor performs well on both objectives in the infinite data…
Adversarial training improves audio classifier robustness.
problem Improving robustness of audio classifiers against adversarial attacks.
method Adversarial training of deep neural networks on audio data.
result Adversarially trained models can resist higher perturbations and fooling rates.
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.
AAT separates robust and non-robust features without supervision.
problem Adversarial vulnerability and accuracy reduction in machine learning models.
method Adversarial Asymmetric Training (AAT) algorithm.
result Preserves accuracy and achieves better disentanglement than previous methods.
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to use the methodology of adversarial training. We analyze the adversarially train…
RATIO improves neural network robustness and explainability.
problem Neural networks' lack of robustness to adversarial changes and uncertainty on out-distribution samples.
method RATIO: Adversarial Training on In- and Out-distribution.
result RATIO leads to robust models with reliable confidence estimates on out-distribution samples.
SPGD improves adversarial training efficiency and accuracy.
problem Improving adversarial training efficiency and accuracy with fewer steps.
method Adversarial-sample generation from a frequency domain perspective, extending PGD to the frequency domain.
result SPGD achieves greater adversarial accuracy compared to PGD with fewer attack steps.
Paper tackles catastrophic overfitting in single-step adversarial training.
problem Catastrophic overfitting leads to sudden drop in robust accuracy.
method Proposes a method to prevent overfitting by using all adversarial examples.
result Demonstrates prevention of catastrophic overfitting and improves robustness.
Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in implementing and deploying this method - expensive in terms of extra memory and computation costs; …
AdvMind detects adversary intent in black-box attacks with high accuracy.
problem Detecting adversary intent in black-box adversarial attacks is challenging.
method AdvMind accounts for adversary adaptiveness and synthesizes queries to expose intent.
result AdvMind detects adversary intent with over 75% accuracy after observing less than 3 query batches.
Adversarial robustness has become a central goal in deep learning, both in the theory and the practice. However, successful methods to improve the adversarial robustness (such as adversarial training) greatly hurt generalization performance on the unperturbed data. This could have a major impact on how the adversarial …
This paper introduces a method to make deep neural networks more robust to adversarial attacks.
problem Deep neural networks are vulnerable to adversarial attacks, leading to incorrect classifications.
method Introduces sensible adversarial learning to balance robustness and natural accuracy.
result Demonstrates that the Bayes classifier is the most robust multi-class classifier under sensible adversarial learning.
It has been demonstrated that deep neural networks are prone to noisy examples particular adversarial samples during inference process. The gap between robust deep learning systems in real world applications and vulnerable neural networks is still large. Current adversarial training strategies improve the robustness ag…
This paper introduces blind adversarial pruning to balance accuracy, efficiency, and robustness in neural networks.
problem Balancing accuracy, efficiency, and robustness in neural networks with limited resources.
method Adversarial pruning with a cutoff-scale strategy to dynamically adjust the strength of adversarial examples.
result Blind adversarial pruning improves the overall AER of pruned models compared to adversarial pruning.
A new method reduces adversarial training time without overfitting.
problem Catastrophic overfitting in single-step adversarial training.
method FGSMPR: FGSM with PGD Regularization.
result Reduces the gap to multi-step adversarial training.
Proposes new loss functions for GANs to improve estimation accuracy and robustness.
problem Improving the training of GANs to achieve more accurate and robust models.
method Introduces Hellinger-type loss functions and analyzes their statistical properties.
result Demonstrates improved estimation accuracy and robustness of the proposed loss functions.