The DoD needs a robust process to evaluate AI/ML model performance and robustness.
problem AI/ML models are brittle and nonrobust, posing risks in national security.
method Reviews AI/ML development process and best practices for evaluation.
result Recommendations for DoD evaluators to ensure robust AI/ML capabilities.
RobustBench aims to standardize adversarial robustness evaluation in image classification.
problem Lack of systematic understanding and error-prone robustness evaluations.
method Standardized benchmark with restricted models and adaptive attacks.
result Reflects current state of the art in adversarial robustness.
Develops a method to evaluate OPE robustness to hyperparameters and policies.
problem Difficulty in selecting and tuning OPE estimators due to limited experimental evaluations.
method Introduces IEOE (Interpretable Evaluation for Offline Evaluation) to assess robustness.
result Demonstrates improved evaluation of OPE estimators' reliability.
New approach for prudent risk evaluation using model aggregation.
problem Risk evaluation and optimization under uncertainty.
method Model Aggregation (MA) approach based on stochastic dominance.
result Produces robust risk evaluation and distributional models.
We introduce a new metric to evaluate corruption robustness of ML classifiers.
problem Evaluating corruption robustness of machine learning classifiers.
method We propose a test data augmentation method using minimal class separation distance to derive a robustness distance ε and a metric MSCR.
result The MSCR metric allows interpretable comparison of classifier robustness on different datasets.
Paper develops robust policy evaluation for reinforcement learning with outlier and heavy-tailed rewards.
problem Outlier contamination and heavy-tailed rewards in reinforcement learning.
method Develops a fully online robust policy evaluation procedure and efficient statistical inference.
result Establishes the Bahadur-type representation of the estimator and develops an online inference procedure.
Generates multimodal safety-critical scenarios for robustness evaluation of decision-making algorithms.
problem Lack of comprehensive evaluation of neural network robustness under real-world scenarios.
method Proposes a flow-based multimodal scenario generator using weighted likelihood maximization and gradient-based sampling.
result Demonstrates improved testing efficiency and multimodal modeling capability compared to traditional methods.
Recently, adversarial deception becomes one of the most considerable threats to deep neural networks. However, compared to extensive research in new designs of various adversarial attacks and defenses, the neural networks' intrinsic robustness property is still lack of thorough investigation. This work aims to qualitat…
Study shows refugee matching gains are robust to different evaluation methods.
problem Stability of refugee matching gains under various evaluation methods.
method Used multiple off-policy evaluation methods including IPW and AIPW.
result Impact estimates remain consistent in magnitude and statistically significant.
Adversarial attacks and the development of (deep) neural networks robust against them are currently two widely researched topics. The robustness of Learning Vector Quantization (LVQ) models against adversarial attacks has however not yet been studied to the same extent. We therefore present an extensive evaluation of t…
This work evaluates risks over time using robust measures and neural networks.
problem Distributionally robust risk evaluation over temporal data.
method Characterizes alternative measures using causal optimal transport, approximates test functions by neural networks, and proves sample complexity.
result Framework outperforms classic counterparts in portfolio selection problems.
Extends insurance-finance arbitrage concept to include model uncertainty.
problem Evaluating hybrid insurance products in uncertain financial markets.
method Introduces robust asymptotic insurance-finance arbitrage and QP-evaluations. result No robust asymptotic insurance-finance arbitrage exists under certain conditions.
Replicated and validated Rank-N-Contrast for robust regression.
problem Deep regression models struggle with continuous sample orders.
method Contrastive learning of continuous representations by ranking samples.
result Improved performance and robustness of RNC framework.
Robust OPE framework uses human inputs to improve policy evaluation in changing environments.
problem Inaccurate policy evaluations due to shifts in environment properties.
method Adapts OPE methods to shifts on user-inputted covariates, providing more realistic utility estimates.
result Robust OPE framework yields less pessimistic policy evaluations and captures realistic dataset shifts.
New method evaluates personalized treatment in critical care, robust to death.
problem Truncation by death in critical care makes traditional DTR evaluation ineffective.
method Principal stratification-based approach, focusing on always-survivor value function, with a semiparametrically efficient, multiply robust estimator.
result Demonstrates robustness and efficiency of the method for personalized treatment optimization.
Compensation methods correct overestimation of adversarial robustness in neural networks.
problem Overestimation of adversarial robustness using first-order attack methods.
method Proposed compensation methods address inaccurate gradient computation and reduce backpropagations.
result Empirical evaluation of adversarial robustness is improved with these methods.
Paper introduces new evaluation criteria for feature-based model explanations.
problem Establishing reliable feature importance explanations for models.
method Robustness analysis using smaller adversarial perturbations.
result New explanations that are necessary and sufficient for predictions.
Paper proposes an ensemble of attacks to evaluate adversarial robustness more reliably.
problem Insufficient evaluation of adversarial defenses leads to incorrect robustness assessments.
method Developed two extensions of PGD-attack and combined them with two complementary attacks.
result Identified several broken defenses with lower robust test accuracy than reported.
Proposes DR algorithms for distributionally robust off-policy evaluation and learning.
problem Sensitive to environment distribution shifts in offline observational data.
method Doubly robust and distributionally robust approaches for OPE/L.
result Achieves semiparametric efficiency and fast regret rate.
VB-Score evaluates AI systems without ground truth, revealing robustness.
problem Evaluating AI systems without ground truth labels, especially for entity-centric tasks.
method VB-Score uses variance-bounded evaluation, constraint relaxation, and Monte Carlo sampling.
result VB-Score reveals robustness differences not seen by conventional frameworks.
We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new policy after every policy gradient update. Despite enormous success of off-policy …
New method reduces sample complexity for robust reinforcement learning.
problem Finite sample analysis in robust reinforcement learning.
method Stochastic approximation framework with controlled bias, using MLMC techniques and geometric truncation.
result Order-optimal sample complexity of ildeO(ε−2) for robust policy evaluation. We study the transfer of adversarial robustness of deep neural networks between different perturbation types. While most work on adversarial examples has focused on L∞ and L2-bounded perturbations, these do not capture all types of perturbations available to an adversary. The present work evaluates 32 attack…
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.
New method reduces over-pessimism in Bayesian control under parameter uncertainty.
problem Over-pessimism in Bayesian control due to misspecified priors.
method Distributionally robust Bayesian control (DRBC) with strong duality and optimization.
result Validated algorithm on synthetic and real data, reducing over-pessimism.
Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts have been made in recent years, it is of great significance to perform correct and complete evaluations of the adversarial attack and defense…
CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extreme Value Theory (EVT) based robustness score for large-scale deep neural networks (DNNs). In this paper, we propose two extensions on this robustness score. First, we provide a new formal robustness guarantee for classifier functions that are twic…
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Unlike recent robustness research, this benchmark evaluates performan…
A new framework evaluates HTE estimators using relative error.
problem Lack of robust evaluation methods for HTE estimators.
method Proposes a relative error-based evaluation framework and neural network architecture to estimate nuisance parameters and robustly compare HTE estimators.
result Demonstrates reliable comparisons and improved HTE estimation through the proposed framework and learning algorithm.
We propose a robust regression approach to off-policy evaluation (OPE) for contextual bandits. We frame OPE as a covariate-shift problem and leverage modern robust regression tools. Ours is a general approach that can be used to augment any existing OPE method that utilizes the direct method. When augmenting doubly rob…
This paper introduces metrics to evaluate robustness of neural networks to natural adversarial examples.
problem Measuring robustness of neural networks to natural adversarial examples.
method Proposes latent space performance metrics based on generative models.
result Latent adversarial perturbations are often perceptually small and associated with classifier accuracy.
In this work, we evaluate adversarial robustness in the context of transfer learning from a source trained on CIFAR 100 to a target network trained on CIFAR 10. Specifically, we study the effects of using robust optimisation in the source and target networks. This allows us to identify transfer learning strategies unde…
The study assesses ML model robustness under worst-case subpopulations.
problem ML model performance degradation under non-training population.
method Two-stage estimation procedure for evaluating worst-case robustness over subpopulations.
result The method certifies model robustness and prevents unreliable deployments.
New method speeds up PGD for CV robustness evaluation.
problem Computational inefficiency of PGD for robustness evaluation.
method Early termination of PGD based on cycle detection.
result Large speedup factors without sacrificing robustness.
This work evaluates uncertainty in deep Gaussian processes.
problem Uncertainty quantification in deep Gaussian processes.
method Hierarchical deep Gaussian processes (DGPs) and Deep Sigma Point Processes (DSPPs) evaluated on regression and classification tasks.
result DSPPs provide strong in-distribution calibration but are less robust under distribution shift compared to ensembles.
Study improves image classifier robustness to random p-norm corruptions.
problem Improving robustness of image classifiers to real-world imperceptible corruptions.
method Training and testing with random p-norm corruptions, evaluating robustness against different p-norms.
result Training with a combination of p-norm corruptions significantly improves robustness.
We consider the problem of robust optimization within the well-established Bayesian optimization (BO) framework. While BO is intrinsically robust to noisy evaluations of the objective function, standard approaches do not consider the case of uncertainty about the input parameters. In this paper, we propose Noisy-Input …
New method for robust policy evaluation in offline reinforcement learning with sequentially exogenous unobserved confounders.
problem Offline reinforcement learning in domains with unobserved confounders.
method Orthogonalized robust fitted-Q-iteration with closed-form solutions and bias-correction.
result Effective in simulations and real-world data, improving robustness and computational ease.
New robustness metric helps select reliable classifiers.
problem Evaluating reliability of classifier predictions.
method Proposed new robustness metric for any classifier and feature type.
result Demonstrated ability to distinguish reliable from unreliable predictions.
Improves off-policy evaluation with imperfect annotations.
problem Limited dataset coverage for evaluating new policies.
method Doubly robust estimators combining IS and DM, incorporating counterfactual annotations.
result Using annotations within the DM component yields the most desirable theoretical results.
Outlier detection is a crucial part of robust evaluation for crowdsourceable assessment of Quality of Experience (QoE) and has attracted much attention in recent years. In this paper, we propose some simple and fast algorithms for outlier detection and robust QoE evaluation based on the nonconvex optimization principle…
The paper tackles robust reinforcement learning with performance guarantees.
problem Finding a robust policy for RMDP with state space uncertainties.
method Proposes RLSPI algorithm for learning optimal robust policy with performance bounds.
result Demonstrates the performance of RLSPI on standard benchmark problems.
ViewFool identifies adversarial viewpoints to test image recognition robustness.
problem Lack of robustness to viewpoint changes in visual recognition models.
method Neural Radiance Fields (NeRF) and entropic regularizer to find adversarial viewpoints.
result Common image classifiers are highly vulnerable to generated adversarial viewpoints.
CausalCompass evaluates TSCD robustness under violations of modeling assumptions.
problem Widespread adoption of TSCD is hindered by untestable causal assumptions and lack of robustness evaluation.
method CausalCompass is a flexible benchmark framework for assessing TSCD robustness under violations of modeling assumptions.
result No single method consistently attains optimal performance across all settings, but deep learning-based methods perform well.
A new estimator for evaluating policies in unknown environments.
problem Evaluating policies when both logging policy and value function are unknown.
method Doubly-Robust (DR) off-policy evaluation (OPE) estimator, DRUnknown, that estimates both the logging policy and value function.
result DRUnknown achieves the smallest asymptotic variance and is optimal when both models are correctly specified.
New method estimates policy performance under unobserved confounding.
problem Estimating policy performance when decisions depend on unobserved variables.
method Developed worst-case bounds for robust OPE under unobserved confounding.
result Efficient procedure for computing worst-case bounds, proving statistical consistency.
AlphaEval evaluates alpha mining models efficiently and comprehensively.
problem Lack of systematic evaluation for alpha mining models.
method Unified, parallelizable evaluation framework assessing predictive power, stability, robustness, financial logic, and diversity.
result AlphaEval achieves evaluation consistency comparable to comprehensive backtesting, providing more comprehensive insights and higher efficiency.
The robustness of neural networks to adversarial examples has received great attention due to security implications. Despite various attack approaches to crafting visually imperceptible adversarial examples, little has been developed towards a comprehensive measure of robustness. In this paper, we provide a theoretical…