Discretizing input space improves DLN robustness against adversarial attacks.
problem Improving machine learning models' resistance to adversarial attacks.
method Input discretization and Binary Neural Networks (BNNs).
result 2-bit input discretization significantly enhances adversarial robustness with minimal accuracy loss.
Study tackles discretization problem in crafting adversarial examples for discrete integer domains.
problem Discretization problem in crafting adversarial examples for discrete integer domains.
method Proposes a black-box method to reduce adversarial example searching to a derivative-free optimization problem.
result Significantly higher success rate in crafting adversarial images in discrete integer domain compared to black-box methods.
Random Gaussian noise and pixel discretization improve image classifier robustness.
problem Whitebox adversarial attacks decrease classifier accuracy.
method Inject random Gaussian noise, discretize pixels, and use any classifier.
result Reduces KL divergence and lower bound on classifier accuracy.
New framework for robustness guarantees in discrete domains.
problem Adversarial robustness in constrained discrete domains.
method Graphical framework for adversarial costs, accommodating complex cost functions.
result Provably minimal adversarial cost and robustness guarantees.
Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.
problem Adaptive discretization in adversarial Lipschitz bandits.
method Adversarial Zooming algorithm for adaptive discretization.
result First algorithm for adversarial Lipschitz bandits with instance-dependent regret bounds.
The paper provides robustness guarantees for classifiers under Gaussian noise and discrete adversaries.
problem Ensuring robustness of classifiers against adversarial attacks.
method Explores robustness guarantees for ensembles of classifiers under Gaussian noise and discrete adversaries, tightening the guarantees with specific assumptions.
result The paper offers robustness guarantees and associated algorithms for discrete adversaries, demonstrating their effectiveness on image and molecule datasets.
Paper develops a method to generate discrete adversarial attacks on text classification models using submodular optimization.
problem Generating adversarial examples for discrete structures like text is challenging.
method Formulated adversarial attacks as an optimization task on submodular set functions, guided by gradient information.
result Achieved a 1-1/e approximation factor for attacks using the greedy algorithm.
Generative Adversarial Networks (GAN) have shown great promise in tasks like synthetic image generation, image inpainting, style transfer, and anomaly detection. However, generating discrete data is a challenge. This work presents an adversarial training based correlated discrete data (CDD) generation model. It also de…
New algorithm defends against adversarial examples in image classification.
problem Defending against adversarial examples in image classification.
method Approximates Discrete Fourier transform of sparse signals corrupted by L0 noise. result Successfully defends against L0 adversaries in image classification. Proposes a new GAN framework for discrete data generation.
problem Difficulty in passing gradients from discriminator to generator for discrete data.
method Adversarial approach with iterative generator definition based on discriminator.
result Improves discrete data generation quality and diversity compared to GANs and ML.
AdvImmune improves certifiable robustness of GNNs against adversarial attacks.
problem Vulnerability of graph neural networks to adversarial attacks.
method Proposes AdvImmune, an algorithm that optimizes with meta-gradient to improve certifiable robustness.
result Remarkably improves the ratio of robust nodes by 12%, 42%, 65% with an affordable immune budget of only 5% edges.
Gradient-based methods for games suffer from discrete update steps that cause drift, affecting performance.
problem Gradient-based methods for two-player games suffer from drift due to discrete update steps.
method Derived modified continuous dynamical systems to closely follow the discrete dynamics of games.
result Identified distinct components of discretization drift that can alter or destabilize game performance.
Tabular GAN generates synthetic tables from datasets.
problem Generating high-quality synthetic tabular data.
method Generative adversarial network (GAN) for tabular data.
result TGAN outperforms conventional models in generating correlated tabular data.
Optimal adversarial attacks minimize mutual information, revealing classifier vulnerabilities.
problem Designing optimal attacks to degrade machine learning performance.
method Information-theoretic approach to finding optimal perturbations.
result Optimal attacks minimize mutual information between degraded and original signals.
Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack scenario trains an additive contribution to the inputs to repurpose the neural network for the new clas…
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.
Graph deep learning models are vulnerable to adversarial attacks, which this paper addresses.
problem Adversarial attacks on graph data models, especially their discreteness and imperceptible perturbations.
method Proposed both attack and defense techniques, including integrated gradients for attacks and graph inspection for defenses.
result Demonstrated the effectiveness of proposed methods through experiments on various datasets.
Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such as pixel discretization are particularly attractive in practice due to their simplicity, low computational overhead, and applicability to var…
The paper connects discrete choice models to multi-armed bandit algorithms with sublinear regret bounds.
problem Optimizing user choices in a multi-armed bandit setting.
method Establishes connections between discrete choice models and multi-armed bandit algorithms, providing sublinear regret bounds and novel algorithms.
result Sublinear regret bounds for a family of algorithms, including the Exp3 algorithm.
Continuous-time algorithms improve online learning performance.
problem Online learning with sequential data and minimizing overall regret.
method Extending discrete-time algorithms to continuous-time models for online linear optimization, adversarial bandit, and adversarial linear bandit.
result Optimal regret bounds are proven for continuous-time settings.
Proposes novel model for estimating SDEs from noisy data.
problem Estimating drift and diffusion from noisy observations of SDEs.
method Adversarial and moment matching inference techniques for SDEs.
result Significant improvements in parameter accuracy and robustness.
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.
Proposes Neural SDE for better model robustness and generalization.
problem Missing regularization mechanisms in Neural ODE networks.
method Integrates various regularization mechanisms via stochastic noise injection.
result Improves robustness and generalization compared to Neural ODE.
Adversarial attacks hide cyber-physical attacks in ICS.
problem Hiding cyber-physical attacks in industrial control systems.
method Modeling an attacker compromising sensors, manipulating data, and evaluating attacks on both continuous and mixed data.
result Successfully hides cyber-physical attacks with 2.87 out of 12 sensors compromised on average.
Motivated by the problem of automated repair of software vulnerabilities, we propose an adversarial learning approach that maps from one discrete source domain to another target domain without requiring paired labeled examples or source and target domains to be bijections. We demonstrate that the proposed adversarial l…
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.
We present a probabilistic framework for studying adversarial attacks on discrete data. Based on this framework, we derive a perturbation-based method, Greedy Attack, and a scalable learning-based method, Gumbel Attack, that illustrate various tradeoffs in the design of attacks. We demonstrate the effectiveness of thes…
Optimal estimator for discrete distributions from faulty batches.
problem Estimating discrete distributions from batches, some of which may be unreliable.
method First polynomial-time estimator achieving optimal accuracy in number of batches.
result Optimal estimation accuracy in polynomial time.
RS-Del provides robustness for sequence classifiers against edit distance attacks.
problem Certifying robustness of discrete sequence classifiers against edit distance attacks.
method Randomized deletion (RS-Del) for discrete sequence classifiers, focusing on edit distance-bounded adversaries.
result Achieved a certified accuracy of 91% at an edit distance radius of 128 bytes on malware detection.
Generative Adversarial Networks (GAN) have limitations when the goal is to generate sequences of discrete elements. The reason for this is that samples from a distribution on discrete objects such as the multinomial are not differentiable with respect to the distribution parameters. This problem can be avoided by using…
Generative adversarial networks (GANs) are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated samples being completely differentiable w.r.t. the generative parameters, and thus d…
The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We propose a framework for generating realistic text via adversarial training. We emp…
Unified analysis of perturbation-based strategies in stochastic and adversarial bandit problems.
problem Optimality of perturbation-based strategies in multi-armed bandit problems.
method Unified regret analysis for stochastic and adversarial settings, using perturbations of sub-Weibull and bounded support.
result Unified bounds for perturbations in both stochastic and adversarial settings, with optimal perturbations of Frechet-type.
We propose Graphical Generative Adversarial Networks (Graphical-GAN) to model structured data. Graphical-GAN conjoins the power of Bayesian networks on compactly representing the dependency structures among random variables and that of generative adversarial networks on learning expressive dependency functions. We intr…
Novel algorithm solves optimal transport using evolving probability distributions and convolution.
problem Sample-based optimal transport problem.
method Adversarial formulation with convolution of adaptive kernel and evolving measure.
result Algorithm robust to dimensionality and produces complex maps.
End-to-end Dyna-AIL combines planning and learning for faster convergence.
problem Efficient imitation learning with minimal interactions.
method Dyna-like framework integrating model-based planning and model-free learning.
result Our approach converges to optimal policies with fewer interactions.
ARL makes market makers resilient to adversarial conditions.
problem Creating resilient market makers against adversarial attacks.
method Transformed single-agent RL into a zero-sum game between market maker and adversary.
result ARL leads to risk-averse behavior and significant performance improvements.
New method for robust learning from batches, even adversarial ones.
problem Learning from batches that may be corrupt or adversarial.
method General framework for robust learning, derived from optimal robust algorithms.
result First robust agnostic learning algorithms for various distributions.
Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the image processing field to the input word embedding space instead of the discrete…
In this paper, we study the generative models of sequential discrete data. To tackle the exposure bias problem inherent in maximum likelihood estimation (MLE), generative adversarial networks (GANs) are introduced to penalize the unrealistic generated samples. To exploit the supervision signal from the discriminator, m…
Paper improves neural network robustness certification with tighter radii estimates.
problem Certifying neural networks' robustness against adversarial attacks.
method Advanced algorithms for discrete and continuous domains, optimizing sample size, standard deviation, and temperature.
result Significant improvement in certified test-set accuracy with tighter certified radii bounds.
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. 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…
Paper proposes IABF to improve NECST robustness.
problem Limited robustness of NECST learned coding networks.
method Infomax Adversarial-Bit-Flip (IABF) to improve stability and robustness.
result IABF achieves state-of-the-art performances on compression and error correction benchmarks.
New method learns population dynamics from snapshots using JKO scheme and inverse optimization.
problem Recovering underlying process governing particle evolution from discrete time samples.
method Combines JKO scheme with inverse optimization techniques for end-to-end adversarial training.
result Improved performance over prior JKO-based methods with theoretical guarantees.
Paper presents an optimization-based attack and defense for graph neural networks.
problem Adversarial robustness of graph neural networks (GNNs).
method Gradient-based attack and optimization-based adversarial training.
result Optimization-based attack can significantly decrease GNN classification performance with minimal edge perturbations.
Generative models learn distributions of continuous functions.
problem Training generative models on discretized grids limits model size and data type.
method Parameterize data points by continuous functions, learn distributions over these functions.
result Models can learn rich distributions of functions independently of data type and resolution.
Framework improves GCNs for graphless and adversarial settings.
problem Improving GCNs without graph data and making them robust to adversarial attacks.
method Joint probabilistic model with variational inference and Concrete distributions.
result Framework outperforms state-of-the-art algorithms on semi-supervised classification.