The paper tackles adversarial robustness by maximizing worst-case mutual information.
problem Training robust machine learning models against adversarial inputs is challenging.
method Develops a notion of representation vulnerability and an unsupervised learning method to maximize worst-case mutual information.
result Proves a lower bound on minimum adversarial risk and supports robustness of representations.
Framework learns fair representations decoupling sensitive attributes.
problem Learning fair representations for unknown sensitive attributes.
method Adversarial learning framework to censor sensitive attributes.
result Demographic parity fairness achieved for downstream tasks.
New method improves graph representations against adversarial attacks.
problem Adversarial robustness in graph contrastive learning.
method Adversarial and edge insertion transformations.
result Promising results in preliminary experiments.
EIGAN learns private representations without centralized data, outperforming state-of-the-art.
problem Private representation learning with multiple ally and adversary attributes.
method Exclusion-Inclusion Generative Adversarial Network (EIGAN) and Distributed EIGAN (D-EIGAN).
result EIGAN and D-EIGAN outperform state-of-the-art methods in accuracy and scalability.
Adversarial techniques learn invariant representations across multiple domains.
problem Domain generalization from diverse studies to unseen domains.
method Adversarial censoring techniques for invariant representation learning.
result Limiting behavior of adversarial loss function as the number of domains grows.
In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those…
Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling the effects of covariates, and disentangling meaningful factors of variation. Unfortunately, learning representations that exhibit invariance …
DBGAN learns graph node representations by balancing distribution consistency.
problem Graph representation learning overfits due to ignoring data distribution.
method DBGAN uses a structure-aware prior distribution and bidirectional adversarial learning.
result DBGAN achieves better trade-off between robustness and dimensionality.
Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to shift closer to the "false" class. Motivated by this observation, we propose to …
In traditional generative modeling, good data representation is very often a base for a good machine learning model. It can be linked to good representations encoding more explanatory factors that are hidden in the original data. With the invention of Generative Adversarial Networks (GANs), a subclass of generative mod…
Adversarial transfer learning improves stress assessment across users.
problem Transfer learning challenges in physiological biosignals.
method Disentangled nuisance-robust representations using adversarial networks.
result Adversarial framework enhances cross-subjects stress assessment.
Paper finds exact global optima for adversarial representation learning.
problem Obtaining data representations invariant to sensitive attributes.
method Spectral learning for linear functions, kernel representation for non-linear functions.
result Exact closed-form expression for global optima with performance guarantees.
Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation. We show that demographic information of authors is encoded in -- and can be recovered from -- the intermediate representations learned by text-based neural classifiers. The …
Neural nets learn robust geometric data representations.
problem Ensuring neural networks are robust to adversarial attacks.
method Topological Data Analysis via persistence diagrams, Lipschitz stability.
result Certified ε-robustness on ORBIT5K dataset. We combine conditional variational autoencoders (VAE) with adversarial censoring in order to learn invariant representations that are disentangled from nuisance/sensitive variations. In this method, an adversarial network attempts to recover the nuisance variable from the representation, which the VAE is trained to pre…
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.
In practice, there are often explicit constraints on what representations or decisions are acceptable in an application of machine learning. For example it may be a legal requirement that a decision must not favour a particular group. Alternatively it can be that that representation of data must not have identifying in…
Reprogram deep models to resist adversarial attacks without changing parameters.
problem Improving deep learning models' robustness against adversarial and noisy inputs.
method Proposes a non-linear robust pattern matching technique and three reprogramming paradigms.
result Demonstrates effective reprogramming of deep models for robustness without altering parameters.
Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabelled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to reconstruct unlabelled input data from a latent representation space. More robust r…
Proposes a non-adversarial method for distribution matching.
problem Stability and optimization challenges in adversarial matching methods.
method Non-adversarial VAE-based matching method with alignment upper bounds.
result Demonstrates applicability of non-adversarial matching methods without modifying original architectures.
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.
New method for model inversion attacks on deep networks.
problem Extracting private information from trained deep learning models.
method Leveraging generative adversarial networks to find realistic class representations.
result Efficiency of model inversion attack within a connected lower-dimensional manifold.
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.
Proposes an adversarial algorithm to learn unbiased representations via HGR coefficient.
problem Learning fair representations without sensitive attribute information.
method Adversarial algorithm using Hirschfeld-Gebelein-Renyi (HGR) maximal correlation coefficient.
result Significant improvements in bias mitigation compared to existing methods.
APGE protects graph node representations from inference attacks.
problem Privacy leakage in graph embedding methods.
method Adversarial training framework with disentangling and purging mechanisms.
result APGE preserves structural and utility attributes while concealing private information.
GGAN improves audio representation learning with fewer labels.
problem Learning representations for specific tasks from unlabelled data.
method Guided Generative Adversarial Neural Network (GGAN).
result GGAN learns better representations with fewer labelled data.
Graph Information Bottleneck (GIB) optimizes graph representations for robustness against adversarial attacks.
problem Challenges in learning graph representations due to structure and feature information.
method GIB is an information-theoretic principle that balances expressiveness and robustness by maximizing mutual information between representation and target, while constraining mutual information with input data.
result GIB-based models are more robust to adversarial attacks, achieving up to 31% improvement.
Proposes adversarial method to estimate Riesz representer.
problem Estimating causal parameters as linear functionals of an underlying regression.
method Adversarial framework using general function spaces.
result Nonasymptotic mean square rate proved for neural networks, random forests, and RKHS.
Theoretical study shows adversarial training improves robustness in deep learning models.
problem Ensuring robustness in pre-trained deep learning models.
method Theoretical analysis of adversarial training and feature purification in two-layer neural networks.
result Adversarial training leads to feature purification, making models more robust to attacks.
The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results showing that the latent space of such generators captures semantic variation in the…
New method speeds up training of deep networks robust to adversarial attacks.
problem Deep networks are sensitive to adversarial perturbations, compromising security and interpretability.
method Fast adversarial training using Euclidean norm approximation and distributed computing.
result Robust feature representations and reduced training time achieved.
The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.
problem Learning structured representations from unlabeled data.
method Adversarial maximization of mutual information between a structured latent variable and a target variable.
result The proposed method outperforms current baselines in document hashing and yields highly compressed interpretable representations.
Deep networks can overfit benignly but still be vulnerable to adversarial attacks.
problem Adversarial vulnerability of deep neural networks trained with benign overfitting.
method Investigated causes of adversarial vulnerability, identified label noise as a key factor, and explored the impact of training procedures and representation learning.
result Adversarial robustness requires more complex decision boundaries than simple ones, suggesting the need for better representation learning.
We provide an approach for learning deep neural net representations of models described via conditional moment restrictions. Conditional moment restrictions are widely used, as they are the language by which social scientists describe the assumptions they make to enable causal inference. We formulate the problem of est…
We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and random. To achieve low dimensionality of learned representations, we propose an easy-to-use, end-to-end trainable, low-rank regularizer (LR) that…
AIB method improves robustness against adversarial perturbations.
problem Optimizing the IB principle for better robustness and understanding compression effects.
method Proposes adversarial information bottleneck (AIB) method to optimize IB principle without explicit distribution assumptions.
result Demonstrates effectiveness in learning more invariant representations and mitigating adversarial perturbations.
Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a more compact and explainable representation of the data. In this paper, we introdu…
Adversarially trained generative models (GANs) have recently achieved compelling image synthesis results. But despite early successes in using GANs for unsupervised representation learning, they have since been superseded by approaches based on self-supervision. In this work we show that progress in image generation qu…
An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings that, as we illustrate, prevent them from fully realizing this goal. In this work, we show that robust optimization can be re-cast as a too…
Proposes GAAE for high-fidelity audio generation and representation learning.
problem Lack of usable representations and high-fidelity audio generation from unsupervised learning.
method Guided Adversarial Autoencoder (GAAE) leveraging a small percentage of labelled data.
result Generates high-fidelity audio with superior quality and learns powerful representations.
New LFR algorithm ensures fair predictions with theoretical guarantees.
problem Ensuring fairness in AI algorithms for social decision-making.
method Proposes a new adversarial training scheme using IPM with a parametric family of discriminators.
result Theoretical guarantee of fairness in final prediction models.
Deep learning methods for person identification based on electroencephalographic (EEG) brain activity encounters the problem of exploiting the temporally correlated structures or recording session specific variability within EEG. Furthermore, recent methods have mostly trained and evaluated based on single session EEG …
This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that also maximizes the mutual information between a small subset of the latent varia…
Proposes a framework for extracting consistent physiological features across users.
problem Variability of biosignals across different users and tasks.
method Adversarial feature extractor for disentangled universal representations.
result Up to 8.8% improvement in average accuracy of classification.
GeoERM learns shared representations on Riemannian manifolds for multi-task learning.
problem Heterogeneous and adversarial tasks in MTL.
method Geometry-aware MTL framework embedding shared representation on Riemannian manifold, optimizing via manifold operations.
result GeoERM improves estimation accuracy and stability, outperforming alternatives.
Paper proposes a new method for learning compact representations of sequential data.
problem Learning compact representations of sequential data capturing spatio-temporal cues.
method Contrastive representation learning via adversarial optimal transport on the Grassmann manifold.
result Empirical results show competitive performance in human action recognition.
Paper improves deep learning models for limit order book data.
problem Deep learning models' performance depends on robust input data representation.
method Identified and modified flaws in existing representations.
result Proposed modifications lead to state-of-the-art performance.
Reduces gender classification bias by learning race-invariant face representations.
problem Societal bias in gender recognition systems.
method Adversarially trained autoencoder model to learn race-invariant face representations.
result Achieved a significant drop of over 40% in racial bias surrogate metric with race invariant representations.