On the Effects of Adversarial Perturbations on Distribution Robustness

• URL: http://arxiv.org/abs/2601.16464v1
• Date: Fri, 23 Jan 2026 05:49:46 GMT
• Title: On the Effects of Adversarial Perturbations on Distribution Robustness
• Abstract summary: Adversarial robustness refers to a model's ability to resist perturbation of inputs.<n> distribution robustness evaluates the performance of the model under data shifts.<n>Prior work has revealed a tradeoff in distribution and adversarial robustness.
• Score: 25.334167445566496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adversarial robustness refers to a model's ability to resist perturbation of inputs, while distribution robustness evaluates the performance of the model under data shifts. Although both aim to ensure reliable performance, prior work has revealed a tradeoff in distribution and adversarial robustness. Specifically, adversarial training might increase reliance on spurious features, which can harm distribution robustness, especially the performance on some underrepresented subgroups. We present a theoretical analysis of adversarial and distribution robustness that provides a tractable surrogate for per-step adversarial training by studying models trained on perturbed data. In addition to the tradeoff, our work further identified a nuanced phenomenon that $\ell_\infty$ perturbations on data with moderate bias can yield an increase in distribution robustness. Moreover, the gain in distribution robustness remains on highly skewed data when simplicity bias induces reliance on the core feature, characterized as greater feature separability. Our theoretical analysis extends the understanding of the tradeoff by highlighting the interplay of the tradeoff and the feature separability. Despite the tradeoff that persists in many cases, overlooking the role of feature separability may lead to misleading conclusions about robustness.

Related papers

• A Multi-Dimensional Evaluation of Explainability in Media Bias Detection [10.798797986346914]
  We present a multi-dimensional evaluation of explainability in encoder-based media bias detection using the Bias s By Experts dataset.<n>We study BERT and RoBERTa as classifiers along three complementary axes: predictive performance, explanation plausibility, and mechanistic faithfulness.<n>Our findings suggest that predictive performance, attribution plausibility, and mechanistic faithfulness characterize different aspects of model behavior.
  arXiv  Detail & Related papers  (2026-07-22T09:29:49Z)
• Debiased Counterfactual Generation via Flow Matching from Observations [4.188178237487111]
  Estimating counterfactual distributions under interventions is central to treatment risk assessment and counterfactual generation tasks.<n>We show that under standard assumptions, observational and counterfactual outcome distributions are tightly linked.<n>These properties motivate learning counterfactual distributions not from scratch, but via a deconfounding flow from the observational distribution.
  arXiv  Detail & Related papers  (2026-05-08T12:35:21Z)
• On the Correlation between Individual Fairness and Predictive Accuracy in Probabilistic Models [42.25718513969163]
  We investigate individual fairness in generative probabilistic classifiers by analysing the robustness of posterior inferences to perturbations in private features.<n>We hypothesise a correlation between robustness and predictive accuracy, specifically, instances exhibiting greater robustness are more likely to be classified accurately.
  arXiv  Detail & Related papers  (2025-09-16T15:17:13Z)
• Identifiable Latent Neural Causal Models [82.14087963690561]
  Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. We determine the types of distribution shifts that do contribute to the identifiability of causal representations. We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
  arXiv  Detail & Related papers  (2024-03-23T04:13:55Z)
• Unveiling the Potential of Probabilistic Embeddings in Self-Supervised Learning [4.124934010794795]
  Self-supervised learning has played a pivotal role in advancing machine learning by allowing models to acquire meaningful representations from unlabeled data. We investigate the impact of probabilistic modeling on the information bottleneck, shedding light on a trade-off between compression and preservation of information in both representation and loss space. Our findings suggest that introducing an additional bottleneck in the loss space can significantly enhance the ability to detect out-of-distribution examples.
  arXiv  Detail & Related papers  (2023-10-27T12:01:16Z)
• Advancing Counterfactual Inference through Nonlinear Quantile Regression [77.28323341329461]
  We propose a framework for efficient and effective counterfactual inference implemented with neural networks. The proposed approach enhances the capacity to generalize estimated counterfactual outcomes to unseen data. Empirical results conducted on multiple datasets offer compelling support for our theoretical assertions.
  arXiv  Detail & Related papers  (2023-06-09T08:30:51Z)
• Explicit Tradeoffs between Adversarial and Natural Distributional Robustness [48.44639585732391]
  In practice, models need to enjoy both types of robustness to ensure reliability. In this work, we show that in fact, explicit tradeoffs exist between adversarial and natural distributional robustness.
  arXiv  Detail & Related papers  (2022-09-15T19:58:01Z)
• Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversaries [69.53730499849023]
  We show that adversarial examples can be successfully transferred to another independently trained model to induce prediction errors. We propose a deep learning-based pre-processing mechanism, which we refer to as a robust transferable feature extractor (RTFE)
  arXiv  Detail & Related papers  (2022-09-14T21:09:34Z)
• Robustness and Accuracy Could Be Reconcilable by (Proper) Definition [109.62614226793833]
  The trade-off between robustness and accuracy has been widely studied in the adversarial literature. We find that it may stem from the improperly defined robust error, which imposes an inductive bias of local invariance. By definition, SCORE facilitates the reconciliation between robustness and accuracy, while still handling the worst-case uncertainty.
  arXiv  Detail & Related papers  (2022-02-21T10:36:09Z)
• Adversarial Robustness under Long-Tailed Distribution [93.50792075460336]
  Adversarial robustness has attracted extensive studies recently by revealing the vulnerability and intrinsic characteristics of deep networks. In this work we investigate the adversarial vulnerability as well as defense under long-tailed distributions. We propose a clean yet effective framework, RoBal, which consists of two dedicated modules, a scale-invariant and data re-balancing.
  arXiv  Detail & Related papers  (2021-04-06T17:53:08Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.