XEnsemble improves DNN robustness against adversarial and out-of-distribution inputs.
problem Protecting DNN models from adversarial and out-of-distribution inputs.
method Diverse input denoising verifiers and disagreement-diversity ensemble learning.
result XEnsemble achieves high defense and detection success rates.
Deep learning models are known to be overconfident in their predictions on out of distribution inputs. There have been several pieces of work to address this issue, including a number of approaches for building Bayesian neural networks, as well as closely related work on detection of out of distribution samples. Recent…
Unified study of out-of-distribution generalization across 172 datasets.
problem Measuring and improving robustness of transfer learning models.
method Collect and fine-tune 31k models on 172 dataset pairs, varying architectures and settings.
result In- and out-of-distribution accuracies increase jointly but their relation is dataset-dependent.
GRAM enhances deep RL for reliable real-world deployment.
problem Generalizing deep RL across in-distribution and out-of-distribution scenarios.
method Introduces a robust adaptation module and a joint training pipeline.
result GRAM achieves strong generalization performance in simulations and hardware.
Regularizes ML algorithms for robust multivariate analysis against distribution shifts.
problem Ensuring robustness of multivariate analysis algorithms against distribution shifts.
method Integrates a causal regularisation term into the loss function of multivariate analysis algorithms.
result Demonstrates improved out-of-distribution generalisation with reduced-rank regression and partial least squares.
New method improves robustness of OOD detection models.
problem Detecting out-of-distribution inputs is critical for deep learning models.
method Proposes ALOE algorithm for robust training with adversarially crafted examples.
result ALOE substantially improves robustness of OOD detection on CIFAR-10 and CIFAR-100 datasets.
Proposes training neural networks to predict uncertainty for out-of-distribution inputs.
problem Poor uncertainty predictions for out-of-distribution inputs limit model robustness.
method Generates pseudo-inputs in low-density regions and trains a Bayesian framework.
result Yields robust and interpretable uncertainty predictions.
A new operator based on t-distributions improves NN classifiers' robustness to out-of-distribution samples.
problem NN classifiers assign extreme probabilities to out-of-distribution samples, leading to unreliable predictions.
method Derive a novel operator using t-distributions to model uncertainty more accurately.
result Classifiers using the new operator are more robust to out-of-distribution samples.
Counterfactual data augmentations may not ensure OOD robustness if performed by a context-guessing machine.
problem Deep learning models lack out-of-distribution robustness due to reliance on spurious features.
method Theoretical analysis and demonstration of counterfactual data augmentations performed by a context-guessing machine.
result Counterfactual data augmentations by a context-guessing machine do not lead to robust OOD classifiers.
Study evaluates methods for improving model robustness to various real-world distribution shifts.
problem Improving model robustness to real-world distribution shifts like geographic changes.
method Introduced new datasets and evaluated existing methods on four types of shifts (style, blurriness, location, camera operation).
result Data augmentations and larger models can improve robustness on real-world distribution shifts, contrary to prior claims.
AROS uses Lyapunov-stabilized embeddings to improve out-of-distribution detection robustness against adversarial attacks.
problem Robust out-of-distribution (OOD) detection against adversarial attacks.
method Neural Ordinary Differential Equations (NODEs) with Lyapunov stability theory for generating robust embeddings.
result Improves robust detection performance significantly, e.g., from 37.8% to 80.1% on CIFAR-10 vs. CIFAR-100.
New framework uses geometry of embeddings to predict robustness.
problem Monitoring robustness in models without OOD labels.
method Constructs graphs from embeddings, measures spectral complexity and curvature.
result Representation geometry predicts robustness reliably.
This paper examines how optimization methods affect the reliability of detecting inputs outside a model's training distribution.
problem The unreliability of deep neural networks on out-of-distribution inputs.
method Analysis of optimization methods' impact on OOD detection approaches.
result Optimization methods significantly influence the robustness of OOD detection approaches.
EntProp increases entropy of clean samples to generate out-of-distribution data for better DNN performance.
problem Improving deep neural networks' accuracy and robustness to out-of-distribution data.
method High entropy propagation using data augmentation and free adversarial training.
result EntProp achieves higher standard accuracy and robustness with lower training cost.
Paper aims to ensure reliable detection of out-of-distribution data with certifiable worst-case guarantees.
problem Deep neural networks are overconfident with OOD inputs, posing safety risks.
method Enforces low confidence and bounds in an l∞-ball around OOD points using interval bound propagation (IBP). result Certifiable worst-case guarantees for OOD detection are possible without significant loss in accuracy.
Deep learning models are known to be overconfident in their predictions on out of distribution inputs. This is a challenge when a model is trained on a particular input dataset, but receives out of sample data when deployed in practice. Recently, there has been work on building classifiers that are robust to out of dis…
Soft labeling impacts OOD detection in neural networks.
problem Impact of soft labeling on OOD detection in deep neural networks.
method Empirical analysis of how soft labeling affects OOD detection performance.
result Soft labeling can either improve or deteriorate OOD detection performance.
In-N-Out improves model robustness to out-of-distribution data.
problem Learning robust models with few in-distribution labeled examples.
method Pre-training with auxiliary information and self-training with pseudolabels.
result In-N-Out outperforms auxiliary inputs or outputs alone on both in-distribution and OOD error.
Medix uses the median to detect outliers from unlabeled data for robust OOD detection.
problem Challenges in using unlabeled data for OOD detection due to mixed InD and OOD samples.
method Introduces Medix, a framework using the median operation to identify outliers from unlabeled data.
result Empirical results show Medix outperforms existing methods in open-world settings.
Proposes DCV-ROOD framework for robust OOD detection evaluation.
problem Ensuring reliable OOD detection methods under diverse conditions.
method Dual Cross-Validation (DCV) adapted for OOD detection evaluation.
result Demonstrates fast convergence to true performance of OOD detection methods.
A new algorithm detects out-of-distribution samples by concentrating them in feature space.
problem Building safe AI systems requires effective out-of-distribution detection.
method The paper proposes a novel algorithm based on the observation that OoD samples concentrate in feature space.
result The algorithm achieves state-of-the-art performance on various OoD detection benchmarks.
New method tackles OOD robustness with a single additional variable.
problem Out-of-distribution generalization with unobserved confounders.
method Identifiability assumptions using a single additional variable.
result Superior empirical performance on benchmark tasks.
MetaPhysiCa tackles robust physics-informed machine learning for OOD tasks.
problem Designing robust PIML methods for OOD forecasting tasks in physics.
method Meta-learning procedure for causal structure discovery including invariant risk minimization.
result Significantly outperforms existing PIML and deep learning methods in OOD tasks.
DRGO improves graph recommendation by mitigating noisy samples and enhancing out-of-distribution generalization.
problem Noisy samples in training data diminish recommendation systems' out-of-distribution generalization.
method DRGO uses a diffusion paradigm to reduce noisy effects and entropy regularization to avoid extreme weights.
result DRGO outperforms current methods in OOD recommendation across various distribution shifts.
MPT improves CNN and energy-based models' OOD detection and generalization.
problem Challenging out-of-distribution detection in computer vision.
method Applying Maximum Probability Theorem as a regularization scheme in CNN and energy-based models.
result MPT-based regularization strategy stabilizes and improves generalization and robustness of base models.
Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This requires a system to reason about its own uncertainty given unfamiliar, out-of-distrib…
Proposes a new prior for VAEs to improve out-of-distribution detection.
problem Probabilistic generative models struggle with out-of-distribution detection.
method Introduces an exponentially tilted Gaussian prior for VAEs.
result Achieves state-of-the-art results on ROC-AUC metric.
Neural networks classify OOD images by their nearest neighbor in training data.
problem Understanding out-of-distribution prediction behavior of neural networks.
method Nearest category generalization (NCG) measure to assess OOD prediction accuracy.
result Adversarially robust networks have higher NCG accuracy than natural training, indicating local regularization impacts decision regions.
Normalizing flows fail to detect OOD data due to learning local pixel correlations.
problem Detecting out-of-distribution data in machine learning systems.
method Investigated why normalizing flows fail to distinguish between in- and out-of-distribution data, and modified flow architecture to improve OOD detection.
result Modifying flow architecture can improve OOD detection by biasing the flow towards learning semantic structure of the target data.
Bayesian autoencoder detects AI safety risk of out-of-distribution inputs.
problem Detecting unreliable predictions from AI models with different distributions.
method Probabilistic, unsupervised Bayesian variational autoencoder with posterior estimation.
result Effective detection of out-of-distribution inputs in both input and latent spaces.
The paper introduces boundary thickness as a measure for improving model robustness.
problem Improving the robustness of machine learning models to adversarial and non-adversarial corruptions.
method Introducing boundary thickness as a measure and showing how various procedures can increase it.
result Thicker decision boundaries lead to improved robustness against adversarial and out-of-distribution transforms.
New methods predict language model out-of-distribution behaviors using causal mechanisms.
problem Predicting how language models behave on unseen data.
method Two methods: counterfactual simulation and value probing.
result Both methods achieve high AUC-ROC and outperform causal-agnostic approaches in out-of-distribution settings.
Calibrated ensembles improve both ID and OOD accuracy in distribution shift.
problem Desired balance between in-distribution and out-of-distribution accuracy.
method Ensemble standard and robust models, calibrating on ID data only.
result ID-calibrated ensembles outperform state-of-the-art methods on multiple datasets.
FROB model improves robustness and reliable confidence for few-shot OoD detection.
problem Challenges in few-shot classification and OoD detection due to limited samples and adversarial attacks.
method FROB model combines support boundary generation and few-shot Outlier Exposure (OE) for improved robustness and reliable confidence.
result FROB achieves generalization to unseen OoD and maintains robustness independent of few-shot number.
Sharp analysis of out-of-distribution error in overparameterized models with importance weights.
problem Understanding and quantifying the degradation of performance in overparameterized models when faced with underrepresented data.
method Sharp analysis of an overparameterized Gaussian mixture model with spurious features and cost-sensitive interpolating solutions incorporating importance weights.
result Characterization of a novel tradeoff between worst-case robustness and average accuracy as a function of importance weight magnitude.
New method uses KL divergence to detect out-of-distribution data effectively.
problem Flow-based models assign higher likelihoods to OOD data than ID data, making OOD detection challenging.
method Proposes a method leveraging KL divergence and local pixel dependence of representations for anomaly detection.
result Demonstrates effectiveness and robustness on prevalent benchmarks.
CreDRO learns credal ensembles via distributionally robust optimization, improving EU quantification.
problem Quantifying predictive epistemic uncertainty in credal models.
method Distributionally robust optimization to capture EU from training randomness and potential distribution shifts.
result Empirically, CreDRO outperforms existing credal methods on various tasks.
PAIR optimizes machine learning models to generalize better to out-of-distribution data.
problem Optimization of machine learning models for out-of-distribution (OOD) generalization often leads to compromises that weaken robustness.
method Introduces a multi-objective optimization (MOO) perspective and a new optimization scheme called PAreto Invariant Risk Minimization (PAIR).
result PAIR improves robustness of OOD objectives by cooperatively optimizing with other objectives, yielding top OOD performances.
A new PLL method uses class activation values to improve robustness.
problem Weakly supervised learning with noisy data and adversarial perturbations.
method Subjective logic with class activation values for uncertainty representation and label weight re-distribution.
result More robust predictions under high noise levels, out-of-distribution examples, and adversarial perturbations.
ACNML method improves uncertainty estimation for deep networks.
problem Uncertainty estimation and calibration for deep neural networks under distribution shift.
method Approximate Bayesian inference to approximate CNML distribution.
result ACNML compares favorably to prior techniques for uncertainty estimation.
WOOD detects out-of-distribution samples using Wasserstein distance.
problem Detecting samples from different distributions in neural networks.
method WOOD defines a Wasserstein-distance-based score to evaluate dissimilarity and solves an optimization problem.
result WOOD consistently outperforms other OOD detection methods.
A large body of recent work has investigated the phenomenon of evasion attacks using adversarial examples for deep learning systems, where the addition of norm-bounded perturbations to the test inputs leads to incorrect output classification. Previous work has investigated this phenomenon in closed-world systems where …
We describe a limitation in the expressiveness of the predictive uncertainty estimate given by mean-field variational inference (MFVI), a popular approximate inference method for Bayesian neural networks. In particular, MFVI fails to give calibrated uncertainty estimates in between separated regions of observations. Th…
Improved VAE model enhances uncertainty estimation for out-of-distribution samples.
problem VAEs assign higher likelihood to out-of-distribution inputs.
method INCPVAE integrates noise contrastive prior into VAEs for reliable uncertainty estimation.
result INCPVAE outperforms standard VAEs in uncertainty estimation for OOD inputs.
RRPI improves offline RL by optimizing policies against worst-case dynamics.
problem Offline RL's performance degrades under distribution shift and transition uncertainty.
method Formulates offline RL as robust policy optimization, treating transition kernel as decision variable.
result RRPI achieves strong average performance on D4RL benchmarks, outperforming recent baselines.
Improved model robustness against corruptions using online adaptation.
problem Machine vision models' vulnerability to image corruptions like blurring or compression artefacts.
method Using corrupted images' statistics for unsupervised online adaptation to improve robustness.
result ResNet-50 achieves 62.2% mCE on ImageNet-C with adaptation, improving from 76.7% without.
Real-time detection of out-of-distribution data in CPS control systems.
problem Detecting out-of-distribution data in CPS control systems for safety.
method Inductive conformal prediction and anomaly detection using variational autoencoders and deep support vector data description.
result Efficient real-time detection with low false alarm rates and comparable execution time.
GCRL learns causal factors for motion forecasting, improving out-of-distribution prediction.
problem Sensitivity to out-of-distribution data in conventional supervised learning methods.
method Generative Causal Representation Learning (GCRL) leveraging causality for knowledge transfer.
result Significantly outperforms prior models on out-of-distribution prediction.