Gray-box attack improves on white-box methods for trading agents.
problem Robustness of Deep RL trading agents against adversarial attacks.
method Hybrid Deep Neural Network policy for gray-box adversarial attack.
result Adversary can reduce trading agent's reward by 214.17%.
Data-driven approach learns effective equations for phase field interfaces.
problem Learning accurate equations for phase field interface dynamics.
method Data-driven identification of partial differential equations from phase field data.
result Data-driven equations outperform analytical approximations in certain regimes.
New method improves model robustness against adversarial attacks.
problem Models trained with adversarial samples can be vulnerable to simple attacks.
method Graybox Adversarial Training using intermediate models to seed adversaries.
result Models trained with Graybox Adversarial Training are more robust to simple attacks.
Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerous misclassifications. We propose a novel way to interpret adversarial perturbations in terms of the effective input signal that classifiers …
Enhances NOAA's Geospace model with machine learning for predicting ground magnetic perturbations.
problem Predicting the probability of ground magnetic field changes.
method Combining physics-based model with machine learning (boosted ensemble of classification trees).
result The ML-enhanced model consistently improves probabilistic forecast metrics.
Randomized diversification defends machine learning models against adversarial attacks.
problem Vulnerability of machine learning systems to adversarial attacks.
method Multi-channel architecture with shared secret key for randomized transforms in a gray-box scenario.
result Increased robustness against various adversarial attacks.
Paper introduces a new method to create adversarial examples against gradient-obfuscating defenses.
problem Crafting adversarial examples to fool gradient-obfuscating defenses.
method Stochastic Substitute Training (SST), a gray-box approach.
result Adversaries can create adversarial examples without knowledge or limited information about the defense.
Paper models buildings' thermal characteristics with a Bayesian approach.
problem Modeling buildings' heat dynamics with various factors.
method Bayesian state-space model incorporating prior knowledge.
result Bayesian approach provides similar parameters as MCMC but faster.
Crop yield forecasting is the methodology of predicting crop yields prior to harvest. The availability of accurate yield prediction frameworks have enormous implications from multiple standpoints, including impact on the crop commodity futures markets, formulation of agricultural policy, as well as crop insurance ratin…
New defense mechanism for deep learning based on cryptography.
problem Vulnerability of deep learning to adversarial attacks.
method Combines machine learning and cryptography to defend against adversarial examples.
result Empirically shows efficiency against various adversarial attacks.
Evaluates SHIELD's effectiveness against adaptive adversaries in various threat models.
problem Evaluating SHIELD's efficacy against adaptive adversaries in different threat models.
method Empirical analysis of SHIELD's robustness against adaptive attacks using Projected Gradient Descent (PGD) attacks in various threat models (white-box, gray-box).
result The targeted PGD attack success rate drops from 64.3% to 48.9% when models are trained from scratch instead of retrained.
ATHENA builds flexible defenses against adversarial attacks.
problem Extensive research on adversarial attacks is domain-specific and cannot be easily extended.
method Designing an extensible framework based on diverse weak defenses.
result Comprehensive empirical study demonstrates the effectiveness of ATHENA.
Paper proposes a method to test and verify control systems with machine learning components.
problem Testing and verifying control systems with machine learning components is challenging.
method Gradient-based method combined with randomized search to find adversarial samples.
result Method outperforms Simulated Annealing optimization in finding adversarial samples.
Proposes FMS for more efficient neural network hyperparameter optimization.
problem Efficient hyperparameter optimization for deep learning models.
method Uses logged checkpoints of trained weights to guide hyperparameter selections.
result Proposes Forecasting Model Search (FMS) method.
We develop an automated variational inference method for Bayesian structured prediction problems with Gaussian process (GP) priors and linear-chain likelihoods. Our approach does not need to know the details of the structured likelihood model and can scale up to a large number of observations. Furthermore, we show that…
Equation discovery method reconstructs model structure and parameters from data.
problem Nonlinear system identification challenges.
method Two interlaced parts: model structure identification and parameter estimation.
result Equation discovery method successfully reconstructs model structure and parameters from data.
Unlike traditional programs (such as operating systems or word processors) which have large amounts of code, machine learning tasks use programs with relatively small amounts of code (written in machine learning libraries), but voluminous amounts of data. Just like developers of traditional programs debug errors in the…
DPC uses physics and neural nets to solve SDEs.
problem Solving stochastic differential equations with missing physics.
method Physics-data fusion with conditional maximum mean discrepancy (CMMD) loss.
result DPC achieves highly accurate solutions on benchmark examples.
New method learns from non-uniform data and partial physical knowledge.
problem Identifying dynamical systems from non-uniformly sampled data.
method Physics-informed neural networks integrating numerical integration methods.
result Learning unknown kinetic rates and estimating parameters from non-uniform data.
NDS learns dynamical models with prior knowledge, improving accuracy and efficiency.
problem Learning accurate dynamical models with limited data and varying dynamics.
method Neural Dynamical Systems (NDS) integrates prior knowledge in ODEs with neural networks to estimate parameters and predict states.
result NDS achieves higher accuracy and uses fewer samples compared to other methods.
Though deep neural networks have achieved state-of-the-art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to the input images are sufficient to fool the most powerful deep neural networks. Va…
Paper builds ML classifier to detect crypto-ransomware.
problem Detecting crypto-ransomware with high accuracy and low false positives.
method Behavior-based detection using input/output activities and file-content entropy. Deep-learning classifier with adversarial research and Integrated Gradient method for explanation.
result Deep-learning classifier achieves high accuracy and low false positive rate in detecting crypto-ransomware.
In recent years, defending adversarial perturbations to natural examples in order to build robust machine learning models trained by deep neural networks (DNNs) has become an emerging research field in the conjunction of deep learning and security. In particular, MagNet consisting of an adversary detector and a data re…
Proposes a framework to identify and correct model-form errors in nonlinear systems.
problem Model-form errors in nonlinear dynamical systems due to unknown or approximated governing equations.
method Uses a hybrid approach combining machine learning and Bayesian filtering to estimate and correct model-form errors.
result Improves the predictive capability of known but approximate governing equations for nonlinear dynamical systems.
MimickNet approximates clinical ultrasound post-processing without proprietary data.
problem Matching proprietary clinical-grade ultrasound post-processing techniques.
method Deep learning framework MimickNet that transforms raw DAS beams into post-processed images.
result MimickNet achieves high SSIM scores (0.930-0.967) on test sets.
Poisoning attacks improve graph-based recommender system recommendations.
problem Designing effective poisoning attacks for graph-based recommender systems.
method Formulated as an optimization problem, solved with techniques to assign rating scores to fake users.
result Outperforms existing attacks for graph-based recommender systems, recommending target items to 580 times more normal users.