Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

65130194259 · Jun 202019922001200920172026
48 results for adversarial shifts

Combines adversarial and interventional robustness for machine learning models.

problem Designing robust models for distribution shifts in machine learning.
method RISe formulation using distributionally robust optimization.
result Demonstrates efficacy of RISe approach with synthetic and real-world datasets.

This paper examines how adversarial perturbations affect model performance and equilibrium learning.

problem Adversarial perturbations and covariate shifts impact model performance and equilibrium learning.
method Characterizes the extrapolation region in regression and classification, analyzes dynamics of adversarial learning games.
result Establishes two directional convergence results: a blessing in regression and a curse in classification.

This work uses adversarial learning to detect and correct feature shifts in various datasets.

problem Detecting and correcting feature shifts in real-world datasets.
method Adversarial learning applied to multiple discriminators to detect and correct feature shifts.
result Mainstream classifiers can effectively localize and correct feature shifts, outperforming existing techniques.

Discrepancy between training and testing domains is a fundamental problem in the generalization of machine learning techniques. Recently, several approaches have been proposed to learn domain invariant feature representations through adversarial deep learning. However, label shift, where the percentage of data in each …

2019-03-15abs ↗pdf ↗

Stable Adversarial Learning improves robustness to distributional shifts.

problem Vulnerability of machine learning algorithms to distributional shifts.
method SAL algorithm that constructs a practical uncertainty set and conducts differentiated robustness optimization based on covariate stability.
result The proposed method uniformly improves performance across unknown distributional shifts.

This paper characterizes and designs loss functions for robust classification with abstention.

problem Ensuring robustness against adversarial attacks and knowing when to abstain from prediction.
method Proposes adversarial robust reject option loss and characterizes surrogates for calibration.
result Shifted Double Ramp Loss and Shifted Double Sigmoid Loss satisfy the calibration conditions.

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.

New method improves robustness in partially observable domains by training against latent distribution shifts.

problem Challenges in robustness under latent distribution shift in partially observable reinforcement learning.
method Formalizes adversarial latent-initial-state POMDP, proves minimax principle, derives best-response inequalities.
result Reduces robustness gaps from 10.3 to 3.1 shots with targeted exposure to shifted latent distributions.

New framework for robust reinforcement learning policies in uncertain environments.

problem Robust reinforcement learning policies in environments with distributional shifts.
method Comprehensive modeling framework centered around robust Markov decision processes (RMDPs).
result Existence and conditions for the dynamic programming principle (DPP) in RMDPs.

New normalization method makes neural networks more robust to adversarial attacks.

problem Adversarial vulnerability of BatchNorm in deep neural networks.
method Identified distribution shift caused by adversarial images, proposed RobustNorm to use inference-time statistics.
result RobustNorm makes models more robust to adversarial attacks without sacrificing BatchNorm benefits.

DART tackles adversarial robustness in domain adaptation without labeled target data.

problem Combining distribution shifts and adversarial examples in unsupervised domain adaptation.
method DART framework that combines standard UDA methods with a generalization bound for adversarial target loss.
result DART significantly enhances model robustness to adversarial attacks compared to state-of-the-art methods.

Algorithm learns a single neuron robustly to shifts and adversarial noise.

problem Learning a single neuron robustly to distributional shifts and adversarial label noise.
method Designs a computationally efficient algorithm using primal-dual framework.
result Recover a vector satisfying a risk bound under adversarial conditions.

The paper addresses adversarial robustness in in-context learning models.

problem Adversarial distribution shifts threaten the reliability of in-context learning models.
method A distributionally robust meta-learning framework is introduced to provide worst-case performance guarantees under Wasserstein-based distribution shifts.
result Model robustness scales with the square root of its capacity and is penalized by the square of the perturbation magnitude.

Enhances adversarial robustness with unlabeled out-of-domain data.

problem Improving robustness of models against adversarial attacks.
method Leveraging unlabeled data from multiple domains to bridge the sample complexity gap in adversarial robustness.
result Better adversarial robustness achieved when unlabeled data comes from a shifted domain.

Batch normalization shifts models to rely more on non-robust features.

problem Understanding the impact of batch normalization on deep neural networks.
method Empirical analysis and a framework for disentangling robustness and usefulness.
result Batch normalization increases reliance on non-robust features, decreasing adversarial robustness.

This paper extends adversarial attacks to produce desired class probability distributions.

problem Easily fooling deep learning models with imperceptible perturbations.
method Probabilistic framework to generate desired class probability distributions.
result The ability to closely approximate any probability distribution for classes while maintaining high fooling rates and preventing detection.

Model predicts counterfactuals under domain shift and inaccessible variables.

problem Runtime domain corruption impairs counterfactual prediction.
method Subsumes counterfactual prediction under domain adaptation, uses adversarial domain adaptation to reduce distribution disparity.
result VEGAN outperforms baselines in individual-level treatment effect estimation.

New method disentangles latent subspaces under correlation shifts.

problem Correlations between factors of variation make disentanglement models less robust.
method Enforces independence between subspaces conditioned on available attributes using adversarial CMI minimization.
result Models are disentangled and robust under correlation shifts, including in weakly supervised settings.

An adversarial bandit problem with memory constraints is studied where only the statistics of a subset of arms can be stored. A hierarchical learning policy that requires only a sublinear order of memory space in terms of the number of arms is developed. Its sublinear regret orders with respect to the time horizon are …

2020-02-26abs ↗pdf ↗

We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which studies norm-constrained adversaries, we shift our focus to unconstrained adversaries. Defenders submit machine learning models, and try to achi…

2018-09-22abs ↗pdf ↗

Study shows current image classification models lack robustness to real-world dataset shifts.

problem Robustness of current image classification models to natural distribution shifts in real datasets.
method Evaluation of 204 ImageNet models in 213 different test conditions.
result Little to no transfer of robustness from synthetic to natural distribution shifts.

Online monitoring system for safety classifiers with shift detection and conformal adaptation

problem Detecting and adapting to distributional shifts in deployed safety classifiers
method Calibrated sequential statistics for online monitoring, conformal abstention for adaptation
result 86.6% valid detection with mean latency of 39.5 steps

Adversarial attacks on probabilistic state-space models affect latent state and policy decisions.

problem Robust reinforcement learning under adversarial observability.
method Analyzing adversarial attacks on linear probabilistic state-space models.
result Demonstrating the influence of adversarial observations on latent state and policy decisions.

Domain adaptation addresses the common problem when the target distribution generating our test data drifts from the source (training) distribution. While absent assumptions, domain adaptation is impossible, strict conditions, e.g. covariate or label shift, enable principled algorithms. Recently-proposed domain-adversa…

2019-03-05abs ↗pdf ↗

New framework ensures valid uncertainty estimates for any data stream changes.

problem Challenges of distribution shifts and adversarial actors in real-world data streams.
method Leveraging Blackwell approachability from game theory, the framework guarantees calibrated uncertainties for any compact space.
result Improves calibration and decision-making for energy systems.

New regularizer improves neural network robustness and generalization.

problem Ineffective weight decay for networks with homogeneous activation functions.
method Proposes an invariant regularizer to penalize intrinsic weight norms.
result Improves generalization and adversarial robustness on various datasets.

It is difficult to be able to imitate well in unknown states from a small amount of expert data and sampling data. Supervised learning methods such as Behavioral Cloning do not require sampling data, but usually suffer from distribution shift. The methods based on reinforcement learning, such as inverse reinforcement l…

2020-01-19abs ↗pdf ↗

Over the last few years, the phenomenon of adversarial examples --- maliciously constructed inputs that fool trained machine learning models --- has captured the attention of the research community, especially when the adversary is restricted to small modifications of a correctly handled input. Less surprisingly, image…

2019-01-29abs ↗pdf ↗

New algorithm mitigates misspecification amplification in regression models with covariate shift.

problem Distribution shift and model misspecification in regression models.
method Developed a new algorithm inspired by robust optimization to avoid misspecification amplification.
result No misspecification amplification while still achieving optimal statistical rates.

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.

Discriminative active learning reduces data annotation costs for domain adaptation.

problem Conditional shift problem hinders domain adaptation between related but different domains.
method Three-stage active adversarial training: invariant feature space learning, uncertainty and diversity criteria, re-training with queried labels.
result Empirical comparisons show the proposed approach is more effective than existing methods.

Proposes MSS to identify causal structure from heterogeneous environments.

problem Distribution shifts between environments violate i.i.d. data assumption.
method Sparse mechanism shift hypothesis, score-based approach.
result Identifies entire causal structure with high probability.

New framework uses OR to ensure AI systems make safe decisions.

problem Ensuring generative AI systems make safe decisions as they gain autonomy.
method Developed a conceptual framework combining flow-based models and adversarial robustness.
result Increased autonomy requires new OR approaches for feasibility, robustness, and stress testing.

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.