Study robustness of split conformal prediction under adversarial attacks.
problem Ensuring distribution-free coverage guarantees in CP under adversarial conditions.
method Theoretical analysis and extensive experiments on split conformal prediction robustness.
result Prediction coverage varies with calibration-time attack strength, enabling control over coverage under adversarial tests.
A new model for sequential prediction handles adversarial examples by allowing abstention.
problem Sequential prediction algorithms fail with adversarial examples, leading to incorrect predictions.
method Proposes a new model that allows abstention from predictions on adversarial examples, scaling error with VC dimension.
result A learner's error scales with the VC dimension of the hypothesis class, matching the stochastic setting.
Game theory helps machine learn better from adversarial queries.
problem Adversarial evasion in machine learning prediction.
method Repeated Bayesian Sequential Game to balance classifier selection and query type.
result Learner selects appropriate classifier for clean vs. adversarial queries.
Enhances deep learning models' robustness against adversarial attacks.
problem Lack of reliable uncertainty estimates and robust defenses for deep learning models.
method Integrates Conformal Prediction principles with adversarial training.
result Introduces OPSA-AT, a defense strategy that enhances robustness and reliability.
Bayesian neural networks are vulnerable to adversarial attacks.
problem Adversarial robustness of Bayesian neural networks.
method Examination of adversarial robustness through three tasks: label prediction, adversarial example detection, and semantic shift detection.
result Bayesian neural networks are highly susceptible to adversarial attacks.
Adversarial tweets can fool stock prediction models, causing financial loss.
problem Vulnerability of stock prediction models to adversarial attacks on social media.
method Solving combinatorial optimization problems with semantic and budget constraints to generate adversarial tweets.
result Adversarial tweets can fool stock prediction models and cause significant financial loss.
Improves model calibration by addressing adversarially unrobust inputs.
problem Miscalibrated predictions and lack of adversarial robustness in neural networks.
method AR-AdaLS, an adaptive label smoothing method that considers adversarial robustness.
result AR-AdaLS improves model calibration, even under distributional shifts.
Proposes online conformal prediction method with adversarial semi-bandit feedback.
problem Online uncertainty quantification with adversarial semi-bandit feedback.
method Formulates online conformal prediction as an adversarial bandit problem and uses regret minimization.
result Achieves long-run coverage guarantee with adversarial semi-bandit feedback.
This paper explores evasion attacks against Bayesian models.
problem Bayesian predictive models are vulnerable to evasion attacks.
method Developed gradient-based attacks for specific point predictions and entire posterior distributions.
result Optimal evasion attacks can be designed against Bayesian models.
Paper proposes a GAN-based method for better next event prediction in business processes.
problem Insufficient training data and sub-optimal network configuration limit deep learning approaches to next event prediction.
method Adversarial training framework using Generative Adversarial Networks (GANs) for sequential temporal data.
result The proposed approach achieves at least as good accuracy as non-adversarial methods and outperforms them in accuracy and prediction earliness.
Work on making classifiers robust against adversarial attacks for top-k predictions.
problem Vulnerability of classifiers to adversarial perturbations, especially for top-k predictions.
method Randomized smoothing to turn any classifier into a robust one, using Gaussian noise.
result Derives a tight robustness in ℓ2 norm for top-k predictions, achieving 62.8% certified top-5 accuracy on ImageNet.
We provide a methodology, resilient feature engineering, for creating adversarially resilient classifiers. According to existing work, adversarial attacks identify weakly correlated or non-predictive features learned by the classifier during training and design the adversarial noise to utilize these features. Therefore…
Study examines uncertainty in adversarially trained models and proposes improved AT methods.
problem Uncertainty quantification in adversarially trained models for safety-critical applications.
method Investigates conformal prediction (CP) for adversarial attacks, proposes Beta-weighting loss with entropy minimization for improved prediction set size (PSS).
result Proposed AT-UR method improves CP efficiency and prediction set size.
Study evaluates predictive uncertainty in malware detection.
problem Detecting dataset shift and adversarial examples in malware detection.
method Re-designed and built 24 Android malware detectors, quantified their uncertainties with nine metrics.
result Predictive uncertainty helps reliable malware detection but not adversarial evasion attacks.
This paper explores tradeoffs between invariance and sensitivity in adversarial examples.
problem Understanding the limitations of existing adversarial defenses.
method Study of invariance-based adversarial examples and their impact on model accuracy.
result Adversarial defenses against sensitivity-based attacks can harm invariance-based attacks, necessitating new approaches.
A method removes treatment-covariate dependence for counterfactual prediction without adversarial training.
problem Counterfactual prediction under assignment bias.
method Information-theoretic approach learning a stochastic representation Z to minimize mutual information with outcomes.
result The method performs favorably in likelihood, counterfactual error, and policy evaluation compared to adversarial baselines.
New insights link no-regret learning to online conformal prediction in adversarial settings.
problem Understanding the relationship between no-regret learning and online conformal prediction in adversarial environments.
method Analysis of existing algorithms and new connections between no-regret learning and conformal prediction.
result No-regret learning algorithms can provide group-conditional coverage guarantees in adversarial settings.
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.
New method defends deep nets against large perturbations perceptible to humans.
problem Vulnerability of deep nets to adversarial attacks with perceptible but not changing predictions.
method Oracle-Aligned Adversarial Training (OA-AT) to align network predictions with Oracle's.
result Achieves state-of-the-art performance at large perturbation bounds (L-inf of 16/255 on CIFAR-10).
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 debiases machine learning predictions to correct bias in regression coefficients.
problem Bias in regression coefficients from machine learning predictions.
method Proposes an adversarial machine learning algorithm to de-bias predictions.
result Adversarial predictions recover true coefficients, while naive predictions are biased.
Deep neural networks are easily fooled high confidence predictions for adversarial samples
We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case conditional label distributions (the adversarial distributions) that (approximately) m…
Neural models often incorrectly predict the same answer to subtly changed questions, even when they should not.
problem Neural models' oversensitivity to adversarial question changes.
method Formulated a noisy adversarial attack to identify and exploit undersensitivity, tested with data augmentation and adversarial training.
result Undersensitivity can be exploited to mislead models, and addressing it improves model performance and robustness.
RTFE provides adversarial robustness to multiple models.
problem Adversarial examples can transfer to other models, compromising robustness.
method Proposes RTFE, a deep learning-based pre-processing mechanism.
result RTFE provides adversarial robustness to multiple independently trained classifiers.
Paper generates natural adversarial examples for hyperspectral data.
problem Creating adversarial examples for black-box models.
method Modified Wasserstein GAN reweights true data distribution.
result Successfully generates adversarial hyperspectral signatures.
In this paper we study leveraging confidence information induced by adversarial training to reinforce adversarial robustness of a given adversarially trained model. A natural measure of confidence is ∥F(x)∥∞ (i.e. how confident F is about its prediction?). We start by analyzing an adversarial training…
This paper contributes a new machine learning solution for stock movement prediction, which aims to predict whether the price of a stock will be up or down in the near future. The key novelty is that we propose to employ adversarial training to improve the generalization of a neural network prediction model. The ration…
Study improves privacy-preserving online prediction from experts with speed-ups.
problem Privacy-preserving online prediction from experts with speed-ups.
method Differentially private federated online prediction algorithms.
result Achieves m-fold regret speed-up with low-loss expert in federated setting. DBU models struggle with robust uncertainty estimates under adversarial attacks.
problem Robustness of DBU models in adversarial settings.
method Investigated robustness of DBU models under adversarial attacks; proposed median smoothing approach.
result DBU models are not robust in indicating correctly and wrongly classified samples, detecting adversarial examples, and distinguishing ID and OOD data.
Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning. Adversarial attacks, which produce adversarial examples, increase the prediction likelihood of a target class for a particular data point. During this process, the adversarial example can be further optimized…
Paper analyzes adversarial training's performance in binary classification.
problem Understanding the generalization performance of adversarial training.
method Derives precise theoretical predictions for adversarial training performance.
result Provides exact asymptotics for test errors of adversarial training.
A new method aggregates generative classifiers to resist adversarial attacks.
problem Adversarial attacks on deep neural networks.
method Rank-aggregating ensemble of generative classifiers trained on intermediate layer responses.
result The ensemble of generative classifiers shows robustness to adversarial attacks.
GGA improves untrustworthy prediction detection in neural networks without retraining.
problem Susceptibility of neural networks to untrustworthy predictions, especially adversarial attacks and out-of-distribution data.
method Geometric Gradient Analysis (GGA) analyzes the geometry of neural network loss landscapes based on saliency maps.
result GGA outperforms existing methods in detecting untrustworthy predictions, including adversarial and out-of-distribution data.
New algorithm explains DNN predictions using adversarial attacks.
problem Incomprehensible complexity of deep neural networks.
method Adversarial machine learning to identify feature importance.
result Consistent and efficient explanations of DNN predictions.
Adversarial attacks reduce deep learning beam selection performance in mmWave 5G.
problem Adversarial attacks degrade deep learning-based beam selection in mmWave 5G.
method Generates adversarial perturbations to RSS inputs to manipulate DNN predictions.
result Significant reduction in IA performance due to adversarial perturbations.
Domain knowledge helps detect adversarial examples in multi-label classification.
problem Detecting adversarial examples in multi-label classification.
method Convert domain knowledge into constraints and inject them into a semi-supervised learning problem.
result Domain-knowledge constraints help detect adversarial examples effectively.
Several dihedral angles prediction methods were developed for protein structure prediction and their other applications. However, distribution of predicted angles would not be similar to that of real angles. To address this we employed generative adversarial networks (GAN). Generative adversarial networks are composed …
Algorithm learns without knowing distribution, reducing error.
problem Sequential prediction with adversarial injections and abstentions.
method Boosting procedure of weak learners for general VC classes.
result Sublinear error guarantees for general VC classes.
Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete picture of uncertainty. We therefore use principled Bayesian methods to capture…
QUAM improves uncertainty quantification in deep learning models.
problem Estimating epistemic uncertainty in deep learning models.
method QUAM identifies regions with high divergence between predictions and a reference model.
result QUAM has lower approximation error of epistemic uncertainty compared to previous methods.
This paper uses GAN and ERMSE to improve stock price movement prediction accuracy.
problem Predicting stock price movement direction is challenging due to complex, incomplete, and fuzzy information.
method The paper proposes a deep learning model using GAN and ERMSE to forecast stock market trends.
result The GAN model outperformed LSTM in predicting stock price movement direction with a 4.35% improvement.
Survey of graph adversarial learning tasks and their attacks and defenses.
problem Uncertainty and unreliability of deep learning models on graphs against adversarial examples.
method Unified problem definition and comprehensive review of existing works.
result Unified definitions and taxonomies for graph adversarial learning tasks.
Adversarial robustness of amortized Bayesian inference is studied, showing it can be improved.
problem Adversarial robustness of amortized Bayesian inference.
method Simulation-based estimation, regularization scheme based on Fisher information.
result Adversarial robustness can be improved with a regularization scheme.
Endogenous randomness emerges from adversarial market learning.
problem Market randomness
method Deterministic adversarial market model
result Out-of-sample profitability collapses to zero.
CGAN fails to improve deterministic sequence predictions, revealing a theoretical limitation.
problem Improving deterministic sequence predictions with CGAN.
method Developed an adversarial content loss approach.
result CGAN does not improve deterministic sequence predictions.
Study on linear regression robustness to adversarial attacks.
problem Adversarial attacks on linear regression models.
method Analysis of prediction error bounds, asymptotic results, convex optimization.
result Adversarial error can grow to infinity with more features, while test error goes to zero.
AGAC uses an adversary to enhance exploration in complex tasks.
problem Sample inefficiency in complex environments, especially in tasks requiring efficient exploration.
method Integrates an adversary into the actor-critic framework to encourage innovative exploration strategies.
result AGAC leads to more exhaustive exploration and outperforms state-of-the-art methods.