New method enhances neural network robustness against adversarial attacks.
problem Enhancing neural network robustness against adversarial attacks.
method Variational framework with per-sample noise level selector.
result Enhanced empirical robustness and certified robustness.
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.
DefenseVGAE defends graph neural networks against adversarial attacks.
problem Vulnerability of GNNs to adversarial structural perturbations.
method Variational Graph Autoencoder (VGAE) to reconstruct graph structure.
result DefenseVGAE reduces adversarial perturbations and boosts GCN performance.
Complex computer simulators are increasingly used across fields of science as generative models tying parameters of an underlying theory to experimental observations. Inference in this setup is often difficult, as simulators rarely admit a tractable density or likelihood function. We introduce Adversarial Variational O…
The paper detects adversarial examples in LECs for regression in CPS using variational autoencoder.
problem Detecting adversarial examples in learning-enabled cyber-physical systems (CPS).
method Inductive conformal prediction using a variational autoencoder regression model.
result The method effectively detects adversarial examples with a short delay in an emergency braking system simulation.
Adversarial training improves graph autoencoder generalization.
problem Improving graph autoencoder generalization.
method Formulated L2 and L1 adversarial training for graph autoencoders and variational graph autoencoders.
result Adversarial training boosts graph autoencoder and variational graph autoencoder generalization.
A new form of the variational autoencoder (VAE) is proposed, based on the symmetric Kullback-Leibler divergence. It is demonstrated that learning of the resulting symmetric VAE (sVAE) has close connections to previously developed adversarial-learning methods. This relationship helps unify the previously distinct techni…
SVAT reduces investment risks by making stock models sensitive to adversarial perturbations.
problem Risk control in stock recommendation models is insufficient, leading to high investment losses.
method SVAT combines adversarial learning and variational perturbation generation to enhance risk awareness.
result SVAT reduces investment risks by more than 30% compared to state-of-the-art baselines.
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.
Improved IFA with Generative Adversarial Networks for high-dimensional latent variables.
problem Limited expressiveness of traditional VAEs in high-dimensional latent variable modeling.
method Introducing Adversarial Variational Bayes (AVB) and Importance-weighted Adversarial Variational Bayes (IWAVB) algorithms.
result IWAVB demonstrated superior expressiveness and higher likelihood compared to IWAE.
Adversarial CCA improves representation learning by allowing more flexible priors.
problem Improving representation learning through more flexible priors.
method Adversarial techniques applied to Deep Variational CCA (VCCA and VCCA-Private).
result Adversarial CCA offers stronger and more flexible priors for representation learning.
We improve the robustness of Deep Neural Net (DNN) to adversarial attacks by using an interpolating function as the output activation. This data-dependent activation remarkably improves both the generalization and robustness of DNN. In the CIFAR10 benchmark, we raise the robust accuracy of the adversarially trained Res…
Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding dis…
This paper combines three techniques to reduce communications in distributed variational inequalities.
problem Efficiently communicating solutions in large-scale distributed variational inequalities.
method Combining similarity, compression, and local steps to reduce communication rounds and cost.
result Best theoretical guarantees of communication complexity and superior performance in adversarial learning experiments.
Generative adversarial networks (GANs) form a generative modeling approach known for producing appealing samples, but they are notably difficult to train. One common way to tackle this issue has been to propose new formulations of the GAN objective. Yet, surprisingly few studies have looked at optimization methods desi…
Paper proposes robust generative models using VAEs.
problem Lack of robustness in generative models.
method Formally defined robust lower bound, optimized during training.
result Generative models become more robust to adversarial attacks.
The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform image-based unsupervised clustering or semi-supervised classification. Combining the power of these two generative models, we introduce Multi-Adversarial Variational autoEncoder Networ…
Improved reliability of machine learning predictions using variational auto-encoders.
problem Individual unreliability of machine learning models.
method Modified variational auto-encoders to identify a low-dimensional space for reliable classification.
result Improved reliability of predictions and robust identification of adversarial samples.
Paper generates diverse, readable adversarial texts from scratch.
problem Text classification models are easily fooled by adversarial examples.
method Trained a conditional variational autoencoder (VAE) with adversarial loss and utilized GANs to generate consistent adversarial texts.
result Successfully generates adversarial texts with higher success rate and acceptable quality.
Generative model simulates financial market price variations from order flow.
problem Simulating intra-day price variations driven by order flow.
method Sequence Generative Adversarial Networks framework applied to model order flow.
result Generated price sequences from generative model better match real price variations.
VERA uses variational inference to jailbreak LLMs without manual optimization.
problem Lack of principled objective for gradient-based optimization in jailbreaking LLMs.
method VERA casts black-box jailbreak prompting as a variational inference problem, training a small attacker LLM to approximate the target LLM's posterior over adversarial prompts.
result VERA achieves strong performance across various target LLMs, demonstrating the value of probabilistic inference for adversarial prompt generation.
Susceptibility of deep neural networks to adversarial attacks poses a major theoretical and practical challenge. All efforts to harden classifiers against such attacks have seen limited success. Two distinct categories of samples to which deep networks are vulnerable, "adversarial samples" and "fooling samples", have b…
Robust RL improves controller robustness to dynamics variations using adversarial populations.
problem Robustness issues in RL when dynamics are perturbed.
method Adversarial population augmentation to the Robust RL formulation.
result Population-based adversarial approach yields more robust and generalizable policies.
Paper proposes a method to improve deep learning models' robustness to real-world variations.
problem Deep learning models fail to generalize to small variations of the input.
method Adversarial mixing with disentangled representations to enforce robustness to real-world transformations.
result Improves generalization and reduces spurious correlations, as shown by experiments.
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…
This paper analyzes β-Variational Classifiers for robustness and adversarial perturbation detection.
problem Limited robustness of deep neural networks in predictions.
method An analysis of β-Variational Classifiers, focusing on their robustness and adversarial perturbation detection. result Novel insights into the generative component of β-Variational Classifiers. Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise the network at the inference time by applying elaborately designed perturbation to input data. Although several defense methods have been proposed to address specific…
Adversarial autoencoder improves music latent space learning.
problem Learning effective latent spaces for symbolic music data.
method Adversarial regularization with Gaussian mixtures.
result MusAE outperforms standard VAEs in reconstruction and interpolation.
The paper learns perturbation sets from data to improve robustness in machine learning.
problem Real-world perturbations are not well characterized in adversarial defenses.
method A conditional generator defines perturbation sets over latent space, with properties for quality measured.
result Learned perturbation sets generate diverse, meaningful perturbations and improve model robustness.
New deep learning model robust to adversarial attacks using stochastic LWTA units.
problem Adversarial robustness in deep learning networks.
method Introduces deep networks with stochastic LWTA activations, combining them with Bayesian non-parametric tools.
result Achieves high robustness to adversarial perturbations, outperforming state-of-the-art methods.
We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the ℓ2 norm on CIFAR-10. We obtain verifiable average case and worst case robustness guarantees, based on the expected and maximum values of the…
The study improves PAC-Bayesian bounds for adversarial generative models.
problem Improving generalization bounds for adversarial generative models.
method Extending PAC-Bayesian theory to generative models, developing bounds for Wasserstein and total variation distances.
result New training objectives for Wasserstein and Energy-Based GANs.
The Importance Weighted Auto Encoder (IWAE) objective has been shown to improve the training of generative models over the standard Variational Auto Encoder (VAE) objective. Here, we derive importance weighted extensions to AVB and AAE. These latent variable models use implicitly defined inference networks whose approx…
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.
This paper shows equivalence between SVGD and BBVI using kernel gradient flows.
problem Bayesian inference methods and their equivalence.
method Formalizes equivalence between SVGD and BBVI using kernel gradient flows.
result BBVI corresponds precisely to SVGD when using the neural tangent kernel.
Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode collapse in the learned generative model by ensuring that it is grounded in all the ava…
New geometric insights reveal properties of adversarial training problems.
problem Adversarial training in binary classification.
method Equivalence with regularized risk minimization and convex relaxations.
result Existence of minimal and maximal solutions, and regular solutions.
Improves GANs training through game theory.
problem Hard training of GANs due to antagonistic networks.
method Rewrote GAN training as a variational inequality and introduced a stochastic relaxed forward-backward algorithm.
result Algorithm converges to an exact solution or a neighborhood of it under monotonicity.
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.
Active learning aims to develop label-efficient algorithms by sampling the most representative queries to be labeled by an oracle. We describe a pool-based semi-supervised active learning algorithm that implicitly learns this sampling mechanism in an adversarial manner. Unlike conventional active learning algorithms, o…
Study adversarial classification with data corruption up to ε, deriving geometric flows.
problem Optimizing classifiers against adversarial data corruption.
method Variational analysis, geometric flows, mean curvature equations.
result Rigorous proof of initial value problem for small ε, global minimizer of adversarial problem.
This work improves disentanglement by preventing style variables from encoding content-related features.
problem Disentanglement of content and style in data representations using Variational Autoencoders.
method Adversarial training with mutual information minimization to prevent content information leakage in style representations.
result The method efficiently separates content and style related attributes and generalizes to unseen data.
Recent years have seen adversarial losses been applied to many fields. Their applications extend beyond the originally proposed generative modeling to conditional generative and discriminative settings. While prior work has proposed various output activation functions and regularization approaches, some open questions …
Half-AVAE enhances VAE for underdetermined ICA with adversarial training.
problem Challenges in ICA under underdetermined conditions.
method Encoder-free VAE with adversarial networks and EE terms.
result Half-AVAE outperforms baseline models in underdetermined ICA.
Generative adversarial networks (GANs) have given us a great tool to fit implicit generative models to data. Implicit distributions are ones we can sample from easily, and take derivatives of samples with respect to model parameters. These models are highly expressive and we argue they can prove just as useful for vari…
Unbalanced GANs stabilize GAN training by pre-training the generator with VAE.
problem Stable training of GANs to avoid mode collapses and improve image quality.
method Pre-train GAN generator with VAE, balance generator and discriminator training, prevent discriminator's early convergence.
result Unbalanced GANs reduce mode collapses and outperform ordinary GANs in stability, convergence, and image quality.
TA-VAAL improves active learning by better utilizing task structures and overall data distribution.
problem High labeling cost limits deep learning applications; active learning selects informative samples.
method Task-aware variational adversarial active learning (TA-VAAL) modifies VAAL by relaxing task loss prediction and using ranking loss information.
result TA-VAAL outperforms state-of-the-arts on various datasets, including balanced and imbalanced labels.
In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does not overcome the curse of dimensionality, but it is independent of the number of layers in the networ…