Proposes a new adversarial gain measure for NLP tasks.
problem Lack of a unified adversarial model for NLP tasks.
method Defines adversarial gain based on control theory.
result Provides a measure for evaluating adversaries and defenses.
PC-GAIN improves GAIN's imputation by incorporating category information.
problem Missing data in incomplete datasets.
method Pre-training with pseudo-labels and incorporating an auxiliary classifier into GAIN.
result Significantly improved imputation quality compared to GAIN.
Adversaries manipulate wireless power allocation to reduce user rates.
problem Adversaries exploit deep learning for power control to decrease communication rates.
method Adversaries craft perturbations to inputs of a DNN to minimize power allocation.
result Adversarial attacks are highly effective and robust to uncertainties.
This paper explores how temporal dependency in audio data can improve robustness against adversarial examples.
problem Mitigating adversarial examples in audio data.
method Exploiting temporal dependency to gain discriminative power against audio adversarial examples.
result Temporal dependency can be used to resist adaptive attacks on audio adversarial examples.
GCNNs gain rotation invariance with more training augmentation, making SVD-Universal more effective.
problem Improving robustness of GCNNs to adversarial attacks.
method SVD-Universal technique applied to GCNNs trained with larger rotations.
result SVD-Universal becomes more effective as GCNNs gain rotation invariance.
We propose a novel method for imputing missing data by adapting the well-known Generative Adversarial Nets (GAN) framework. Accordingly, we call our method Generative Adversarial Imputation Nets (GAIN). The generator (G) observes some components of a real data vector, imputes the missing components conditioned on what …
Optimal algorithm reduces regret in adversarial bandit problem with multiple plays.
problem Minimizing regret in adversarial bandit problem with multiple plays.
method Introducing a new expert advice algorithm for multiple-play setting, achieving minimax optimal regret bounds.
result Minimizes regret asymptotically to the best switching strategy with optimal bounds.
Unlabeled data improves adversarial robustness in machine learning.
problem Improving robustness of machine learning models against adversarial attacks.
method Semisupervised learning with self-training using unlabeled data.
result Semisupervised learning with unlabeled data significantly improves adversarial robustness.
Adversaries with multiple antennas can fool deep learning modulators more effectively.
problem Improving evasion attacks on deep learning-based modulation classifiers.
method Utilizing multiple antennas to enhance adversarial attacks on deep learning classifiers.
result Adversarial attacks with multiple antennas significantly improve classifier accuracy.
The paper introduces a method to improve adversarial robustness in neural networks using randomized perturbations.
problem Deep neural networks are sensitive to small perturbations on correctly classified examples, leading to erroneous predictions.
method The approach uses randomized perturbations to optimize the worst case loss function over all possible substitutions of training examples, ensuring that substitution likelihood is weighted by the proximity to the original word.
result The method achieves performance gains and differentially-private model training, improving robustness against adversarial attacks.
The paper shows tree models are vulnerable to adversarial examples and develops a robust algorithm.
problem Vulnerability of tree-based models to adversarial examples.
method Develops a novel algorithm to learn robust trees by optimizing performance under worst-case perturbation of input features.
result The proposed algorithms substantially improve the robustness of tree-based models against adversarial examples.
Adversarial training overfits, harming robustness; early stopping fixes this.
problem Adversarial robustness in deep learning overfits to training data.
method Empirical study of adversarially trained deep networks.
result Overfitting to training data harms robust performance in adversarial training.
Paper proposes WGAIN for missing feature reconstruction.
problem Missing data in datasets.
method Wasserstein Generative Adversarial Imputation Network (WGAIN) compared to traditional methods.
result WGAIN outperforms traditional methods in imputing missing data.
Study makes code models robust to small changes that keep functionality.
problem Vulnerability of deep neural networks to adversarial examples in source code.
method Defined a powerful adversary and adversarial training to learn robust models.
result Significant gains in robustness demonstrated across different languages and architectures.
New strategy uses interpretability to improve adversarial learning.
problem Improving adversarial learning speed and effectiveness.
method Spatially constrained one-pixel adversarial perturbations guided by gradient-based interpretability.
result Spatially constrained one-pixel adversarial perturbations noticeably improve convergence and attack success.
Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to adversarial example attack, which generates malicious output by adding slight perturbation…
This work increases shape bias in CNNs trained on ImageNet, improving robustness without accuracy gain.
problem Shape bias in CNNs trained on ImageNet.
method Uses domain-adversarial training to remove texture clues and increase shape bias.
result The method increases robustness of CNNs without improving accuracy.
Adaptive networks improve model robustness through conditional normalization.
problem Limited robustness of adversarial-trained networks due to network capacity and training samples.
method Proposes a conditional normalization module to adapt networks during adversarial training.
result Adaptive networks outperform both clean validation accuracy and robustness compared to non-adaptive counterparts.
Charmer improves character-level adversarial attacks for language models.
problem Efficiency and effectiveness of character-level adversarial attacks for language models.
method Query-based adversarial attack method that maintains semantic similarity.
result Charmer achieves high attack success rate and similar adversarial examples.
The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into incorrectly predicting a specified target with high confidence. Current work on fool…
Debona improves neural network verification by faster and tighter bounds.
problem Proving adversarial robustness of neural networks is computationally hard.
method Decouples upper and lower bounds computation, re-implements Neurify.
result 94% reduction in runtime for proving robustness of max-pooling layers.
New method improves adversarial robustness without extra training steps.
problem Improving robustness of deep learning models against adversarial attacks.
method Guided Complement Entropy (GCE) training paradigm.
result GCE achieves better adversarial robustness with improved performance.
Paper studies how to make reinforcement learning agents generalize better.
problem Creating agents that can apply learned knowledge to new, similar tasks.
method Data augmentation, meta-learning, adversarial training.
result Data augmentation method proved effective for policy generalization.
New method reduces adversarial training time by up to 2.5x with comparable accuracy.
problem High computational complexity of adversarial training for deep neural networks.
method Replacing initial adversarial training with natural training.
result Significant reduction in training time (up to 2.5x) without loss in accuracy.
PML-GAN tackles noisy multi-label annotations using adversarial learning.
problem Learning multi-label models from noisy, overcomplete annotations.
method PML-GAN uses a disambiguation network and a generative adversarial network to map noisy labels to clean labels and data samples.
result PML-GAN achieves state-of-the-art performance on partial multi-label learning datasets.
TRASHFIRE improves model robustness by analyzing training rates and costs.
problem Understanding and predicting model robustness under adversarial conditions.
method Survival models, worst-case examples, cost-aware analysis.
result Deeper models offer marginal robustness gains due to inference time, not inherent robustness.
Facebook's ResNeXt WSL models show exceptional robustness against image corruptions and adversarial attacks.
problem Image recognition model robustness against corruptions and adversarial attacks.
method Training with 1B images from Instagram and fine-tuning on ImageNet.
result ResNeXt WSL models achieve state-of-the-art results on ImageNet-C, ImageNet-P, and ImageNet-A.
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.
Kempe discusses NTK approach to machine learning problems.
problem Generally unsolvable machine learning problems.
method NTK approach focusing on kernel formulations.
result Practical applications like data distillation and adversarial robustness.
Enhances neural networks' robustness against adversarial samples without sacrificing clean sample generalization.
problem Limited generalization and time complexity of adversarial training.
method Feature Pyramid Decoder (FPD) framework that integrates denoising and image restoration modules into CNNs and constrains the Lipschitz constant.
result FPD-enhanced CNNs achieve sufficient robustness against general adversarial samples on various datasets.
TAnoGan detects anomalies in time series data using GANs.
problem Anomaly detection in time series data.
method Generative Adversarial Networks (GAN) for unsupervised anomaly detection.
result TAnoGan outperforms traditional and neural network models in anomaly detection.
Paper provides robustness bounds for GNNs against adversarial attacks.
problem Adversarial robustness of GNNs for graph-related tasks.
method PAC-Bayesian framework applied to GCN and MP-GNN.
result Spectral norms of diffusion matrix and weights govern robustness.
We propose a reinforcement learning solution to the \emph{soccer dribbling task}, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best…
MD-CGAN models forecast time series with probabilistic posterior distributions.
problem Limited applications of GANs in time series forecasting, especially with probabilistic predictions.
method Mixture Density Conditional Generative Adversarial Model (MD-CGAN) using Gaussian mixture output.
result MD-CGAN outperforms benchmarks, especially in noisy time series.
Pre-training improves model robustness and uncertainty.
problem Improving model robustness and uncertainty in machine learning.
method Adversarial pre-training and task-specific methods.
result Approximately a 10% absolute improvement in adversarial robustness.
Maximizes robustness in Bayesian experimental design under model uncertainty.
problem Brittleness of Bayesian experimental design under model misspecification.
method Formulates as a max--min game, uses Sibson's α-MI, and adopts PAC-Bayes framework.
result Establishes robust belief update and conditional information gain measure.
Adversarial training improves robustness against common corruptions.
problem Improving robustness of models against common corruptions.
method Adversarial training with ℓp perturbation and learned perceptual similarity. result Our approach leads to state-of-the-art performance on common corruptions.
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.
Study on adversarial attacks on user identification systems using motion sensors.
problem Adversarial attacks on deep learning models for user identification based on motion sensors.
method Study of adversarial example generation methods and their impact on user identification systems.
result Deep neural networks trained for user identification based on motion sensors are vulnerable to adversarial attacks, leading to high misclassification rates.
Study shows flipping a small subset of labels can severely damage machine learning models.
problem Adversarial attacks on distributed machine learning models.
method Formalized label flipping attacks, proposed a greedy algorithm, demonstrated with logistic regression models.
result A budget of only 0.1% of labels at each training step can reduce model accuracy by 6%, and some models can perform worse than random guessing when up to 25% of labels are flipped.
Paper analyzes game dynamics with negative momentum for improved stability and convergence.
problem Complexity and instability in game dynamics, especially in adversarial settings.
method Analyzed gradient-based methods with negative momentum on simple games and adversarial problems.
result Alternating gradient updates with negative momentum achieve convergence in difficult adversarial problems.
Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition. They map the autoencoder's bottleneck layer output (termed as code vectors) to different no…
Adversarial learning reduces racial bias in recidivism prediction models.
problem Racial bias in recidivism prediction scores.
method Adversarial training of neural networks to remove bias.
result Achieved two out of three fairness measures: parity and equality of odds.
This work explores how neural architecture search can improve adversarial robustness without adversarial training.
problem Improving adversarial robustness of neural networks without adversarial training.
method Experimented with hand-crafted and NAS-based architectures to compare robustness to PGD attacks.
result NAS-based architectures are more robust for small-scale attacks, but hand-crafted architectures are more robust for larger datasets and tasks.
Empirical study shows interpretable gradients improve adversarial robustness.
problem Connecting adversarial robustness and model interpretability.
method Introduced Interpretation Regularization (IR) to encourage interpretable gradients.
result Training models to have interpretable gradients improves adversarial robustness.
New method GSAT improves robustness against structured perturbations.
problem Structured perturbations in biological data.
method Formulates GSAT as a non-convex concave minimax optimization problem and solves it with GDADMM.
result Improves robustness against group-sparse and rank-constrained perturbations.
Paper proposes transforming ATN to attack multivariate time series models.
problem Generating adversarial samples for multivariate time series classification models.
method Proposes using a distilled model as a surrogate to mimic attacked models and applies 1-NN DTW and FCN attacks.
result Both models were susceptible to attacks on all 18 datasets.
In recent times, many of the breakthroughs in various vision-related tasks have revolved around improving learning of deep models; these methods have ranged from network architectural improvements such as Residual Networks, to various forms of regularisation such as Batch Normalisation. In essence, many of these techni…