Bayesian adversaries can outsmart traditional adversarial attacks.
problem Bayesian adversaries can manipulate machine learning models through small perturbations.
method Developed a continuous-time particle system (Abram) to approximate the gradient flow of the Bayesian adversarial robustness problem.
result Abram approximates the minimizer of the Bayesian adversarial robustness problem under certain assumptions.
We analyze adversarial learning using a minimax approach.
problem Analyzing risk bounds in adversarial learning problems.
method Reducing adversarial learning to a minimax statistical learning problem and proving a new risk bound.
result Deriving adversarial risk bounds for SVMs, deep neural networks, and PCA.
A novel method to train networks from each other's adversarial examples to resist black-box attacks.
problem Machine learning models can be fooled by adversarial examples, especially in black-box attacks.
method Simultaneous adversarial training combining two networks to learn from each other's adversarial examples.
result The method improves the networks' resilience to black-box attacks.
New reformulations for multiclass classification problems using optimal transport.
problem Adversarial multiclass classification problems.
method Multimarginal optimal transport formulation.
result Reveals geometric structure and extends binary classification results.
Classification problems in security settings are usually contemplated as confrontations in which one or more adversaries try to fool a classifier to obtain a benefit. Most approaches to such adversarial classification problems have focused on game theoretical ideas with strong underlying common knowledge assumptions, w…
This work proposes a new adversarial training method based on L2L framework.
problem Training robust neural networks against adversarial attacks.
method Generic learning-to-learn (L2L) framework to learn an optimizer and a robust classifier.
result L2L outperforms existing adversarial training methods in classification accuracy and computational efficiency.
Adversarial training improves linear regression solutions, revealing sparsity and abrupt interpolation.
problem Adversarial attacks on linear regression models.
method Formulated as a convex problem, adversarial training is used to find robust solutions that are sparse and interpolate data.
result Adversarial training with small disturbances gives the solution with the minimum-norm that interpolates the training data, revealing abrupt transition into interpolation.
TEAM uses Taylor expansion to generate adversarial examples.
problem Vulnerability of deep neural networks to adversarial examples.
method Approximates DNN output using Taylor expansion and optimizes with Lagrange multiplier method.
result Improves robustness of DNNs through adversarial training.
Study proves existence of robust classifiers in multiclass adversarial training.
problem Proves existence of robust classifiers in multiclass adversarial training.
method Three models of adversarial training in multiclass classification, proving existence of Borel measurable robust classifiers.
result Proves existence of Borel measurable robust classifiers in each model.
ARL algorithm reduces adversarial MDP to bandit problems for reliable policy learning.
problem Learning reliable policies in non-stationary, adversarial MDPs.
method Adversarial Reinforcement Learning (ARL) algorithm that converts MDP to a sequence of adversarial bandit problems.
result Achieves optimal regret bound of O ( S A T H 3 ) O(\sqrt{SATH^3}) O ( S A T H 3 ) . 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.
The paper explores why adversarial attacks are inevitable for certain classifiers.
problem The inevitability of adversarial attacks on neural networks.
method Theoretical analysis and experiments on classifier robustness.
result Adversarial examples are inescapable for certain classes of problems.
New algorithm optimally identifies best arm in both stochastic and adversarial settings.
problem Best arm identification in stochastic and adversarial reward scenarios.
method Parameter-free algorithm designed to be robust to adversarial rewards and optimal in stochastic problems.
result Algorithm's error rate matches optimal bounds in stochastic problems and is robust to adversarial rewards.
ALPS improves neural network robustness and generalization.
problem Challenges in designing effective regularization schemes for adversarial robustness.
method Adversarial Labelling of Perturbed Samples (ALPS) using synthetic samples and min-max formulation.
result ALPS achieves state-of-the-art regularization performance and adversarial robustness.
Linear classifiers can resist adversarial attacks on Gaussian data.
problem Adversarial attacks on high-dimensional data.
method Adversarial training of linear classifiers on Gaussian data.
result Linear classifiers can resist adversarial attacks on Gaussian data.
Optimizes deep learning training by treating it as an optimal control problem.
problem Fragility of deep neural networks to adversarial inputs.
method Formulates adversarial training as a min-max optimization problem and interprets it as an optimal control problem.
result Provides the first convergence analysis of adversarial training algorithm.
This paper tackles adversarial examples in NLI models by integrating logical background knowledge.
problem Generating adversarial examples that violate logical constraints in NLI models.
method Reduces adversarial example generation to combinatorial optimisation, using a language model to generate plausible examples.
result Significantly improves NLI model accuracy on adversarial datasets, up to 79.6% relative improvement.
Study stabilizes adversarial training in neural networks over infinite-dimensional spaces.
problem Stability issues in adversarial training of neural networks.
method Functional analysis of minimax optimization over infinite-dimensional spaces of continuous functions and probability measures.
result Convergence property of minimax problems under certain conditions, interpreted as stabilization techniques.
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.
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.
Efficient algorithms speed up adversarial training for linear models.
problem Adversarial training for linear models is computationally expensive.
method Tailored optimization algorithms for regression and classification.
result Significantly faster convergence rates for large-scale problems.
Paper tackles online allocation problems using adversarial training.
problem Online bipartite matching, especially in AdWords.
method Constructs a framework combining game theory, adversarial training, and GANs.
result Designs robust algorithms that perform well under practical and adversarial conditions.
New algorithm reduces regret in corrupted bandits.
problem Stochastic multi-armed bandits with adversarial corruption.
method A new algorithm that is agnostic to corruption levels.
result Regret is nearly optimal and can handle significant corruption.
Proposes an adversarial framework for handling imbalanced data.
problem Handling imbalanced data in classifier training.
method Adversarial approach to weight majority class samples.
result Boosts classifier performance on imbalanced data.
New method detects adversarial attacks in industrial systems.
problem Adversarial attacks compromise machine learning models in industrial control systems.
method Introduces domain adaptation layer and Monte Carlo simulation for proactive defense.
result Approximates Bayes optimal mitigation for improved detection model health.
Heuristics for solving privacy setting problems in neural networks.
problem Maximin problem in generative adversarial privacy setting.
method Greedy algorithm for linear adversaries and alternately optimizing for CNN adversaries.
result The greedy algorithm performs better as the number of instances increases.
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.
Memory-limited learning tackles adversarial bandits with reduced storage.
problem Adversarial bandit problem with limited memory storage.
method Hierarchical learning policy with sublinear memory requirement.
result Established sublinear regret bounds for weak and shifting regrets.
SPAT improves adversarial robustness by preserving semantics in adversarial training.
problem Adversarial examples often have different semantics than original data, introducing unintended biases.
method Semantics-preserving adversarial training (SPAT) that encourages pixel perturbation shared among all classes.
result SPAT improves adversarial robustness and achieves state-of-the-art results in CIFAR-10 and CIFAR-100.
Study efficient learning of robust halfspaces with noise.
problem Learning robust halfspaces in the presence of adversarial perturbations and random label noise.
method Provides conditions for robust learnability and a simple algorithm for any ℓ_p perturbation.
result Simple computationally efficient algorithm for robust learning with random label noise.
The paper sets lower bounds for adversarial robustness in multiclass classification.
problem Adversarial robustness in multiclass classification with arbitrary loss functions.
method Dual and barycentric reformulations for robust risk minimization.
result Sharp lower bounds for adversarial risks are computed efficiently.
New bounds for classifier robustness to adversarial attacks.
problem Characterizing robustness of classifiers to adversarial perturbations.
method Introducing function transformations to relate adversarial risk to standard learning-theoretic risk bounds.
result Error rates on the same order as generalization error of original function classes.
Adversarial examples mislead deep learning models in medical image segmentation.
problem Vulnerability of deep learning models to adversarial examples in medical image segmentation.
method Proposed Adaptive Segmentation Mask Attack (ASMA) to craft targeted adversarial examples.
result Demonstrated vulnerability of deep learning models to adversarial examples in medical image segmentation.
New method simplifies and improves imitation learning without adversarial techniques.
problem Stable optimization and convergence issues in adversarial imitation learning methods.
method Proposes a non-adversarial framework for imitation learning, providing stronger convergence guarantees.
result Shows AIRL as a special case and derives new algorithms for offline imitation learning.
New algorithms improve online prediction from experts with privacy constraints.
problem Online prediction from experts under privacy constraints.
method Proposed and analyzed new algorithms for approximate and pure differential privacy.
result Achieved improved regret bounds for various adversaries.
The paper studies how to make machine learning models robust to adversarial attacks.
problem Making machine learning models robust to adversarial attacks.
method The paper uses Rademacher complexity to study adversarially robust generalization.
result The adversarial Rademacher complexity has an unavoidable dimension dependence, unless the weight vector has bounded ℓ 1 \ell_1 ℓ 1 norm. A new method for estimating adversarial strategies in nonlinear systems.
problem Inferring an intelligent adversarial agent's strategy in highly nonlinear systems.
method Formulated inverse cognition as a nonlinear Gaussian state-space model and developed an inverse UKF (IUKF) system.
result The estimation error of IUKF converges and closely follows the recursive Cramér-Rao lower bound.
The paper improves smoothed analysis for online problems with adaptive adversaries.
problem Online prediction, discrepancy minimization, and online optimization with adaptive adversaries.
method General technique to prove smoothed guarantees against adaptive adversaries, reducing to simpler oblivious adversaries.
result Strong smoothed guarantees for three online problems, matching or improving previous results.
Method creates resilient classifiers by focusing on highly predictive features.
problem Adversarial attacks exploit weakly correlated features learned during training.
method Resilient feature engineering to prioritize highly predictive features.
result Serial and Parallel Composition Resilience theorems support the design of resilient classifiers.
Adversarial robustness improved by abstaining from decisions.
problem Improving classification accuracy in the presence of adversarial perturbations.
method Introducing an abstain option in binary classification problems, using metrics to quantify performance and robustness.
result There is a tradeoff between nominal performance and adversarial robustness.
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.
We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching. Within a framework of conditional entropy, we propose both adversarial and non-adversarial approaches to learn desirable matched joint distributions for unsupervised and supervised tasks. We…
Free adversarial training improves robustness without generating adversarial examples.
problem Training robust models against adversarial attacks is costly and impractical for large-scale datasets.
method Recycles gradient information from parameter updates to generate adversarial examples.
result Free adversarial training achieves comparable robustness to PGD training at negligible cost.
Paper proposes an efficient algorithm to compute minimum adversarial perturbation for NN classifiers.
problem Computing the minimum adversarial perturbation for Nearest Neighbor classifiers.
method Formulated as a list of convex quadratic programming problems, solved using efficient algorithms.
result Shows dual solutions as valid lower bounds for adversarial perturbation, aiding robustness verification.
Paper improves adversarial training using a learned optimizer.
problem Improving robustness of deep learning models against adversarial attacks.
method Empirically identified PGD attack's limitations and used a learning-to-learn framework to train an adaptive inner optimizer.
result The proposed framework consistently improves model robustness over traditional adversarial training methods.
Survey of GANs and autoencoders, addressing mode collapse and likelihood issues.
problem Addressing mode collapse and likelihood issues in GANs and autoencoders.
method Explains various GAN and autoencoder variants, their applications, and methods to resolve issues.
result Various methods to resolve mode collapse and improve likelihood in GANs and autoencoders.
Adversarial training improves linear regression solutions, offering robustness against small perturbations.
problem Vulnerability of linear models to adversarial perturbations.
method Formulated as a min-max problem, adversarial training minimizes the best solution under worst-case attacks.
result Adversarial training yields the minimum-norm interpolating solution in overparameterized models, equivalent to parameter shrinking methods in underparameterized models.
Analyzes biased random walks and corrupted intervals in adversarial settings.
problem Learning thresholds and intervals in adversarial conditions.
method Analyzes biased random walks and corrupted intervals under adversarial design.
result Analyzes the expected behavior of biased random walks and corrupted intervals.