Lune

CVPR Findings2026

A Robust Out-of-Distribution Detection Framework via Synergistic Smoothing

Maria Stoica, Abdelrahman Hekal, Alessio Lomuscio

Abstract

Reliable out-of-distribution (OOD) detection is a critical requirement for the safe deployment of machine learning systems. Despite recent progress, state-of-the-art OOD detectors are highly susceptible to adversarial attacks, which undermines their trustworthiness in automated systems. To address this vulnerability, we apply median smoothing to baseline OOD detection scores, balancing clean and adversarial accuracies. Our key insight is that the noisy samples generated for median smoothing can be repurposed to quantify the local instability of the base score. We observe that OOD samples exhibit higher instability under perturbation. Based on this, we propose ROSS, a novel and robust post-hoc OOD detector that leverages the instability of baseline scores to further distinguish between in-distribution (ID) and OOD samples. ROSS achieves symmetric robustness, performing strongly against both score-minimising and score-maximising attacks, unlike prior work. This symmetric defence leads to state-ofthe-art robustness, outperforming prior methods by up to 40 AUROC points. We demonstrate ROSS's effectiveness on extensive experiments across CIFAR-10, CIFAR-100, and Im-ageNet.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Fast Decision Boundary based Out-of-Distribution Detector cites Energy-based Out-of-distribution Detection
  • Fast Decision Boundary based Out-of-Distribution Detector cites ReAct: Out-of-distribution Detection With Rectified Activations
  • Fast Decision Boundary based Out-of-Distribution Detector cites Out-of-Distribution Detection with Deep Nearest Neighbors
  • ReAct: Out-of-distribution Detection With Rectified Activations cites Energy-based Out-of-distribution Detection
  • Out-of-Distribution Detection with Deep Nearest Neighbors cites Energy-based Out-of-distribution Detection
  • Out-of-Distribution Detection with Deep Nearest Neighbors cites ReAct: Out-of-distribution Detection With Rectified Activations
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on11

  1. Energy-based Out-of-distribution DetectionWeitang Liu, Xiaoyun Wang, John D. Owens, Yixuan LiNeurIPS 2020 · 2,213 citations
  2. Out-of-Distribution Detection with Deep Nearest NeighborsYiyou Sun, Yifei Ming, Xiaojin Zhu, Yixuan LiICML 2022 · 789 citations
  3. ReAct: Out-of-distribution Detection With Rectified ActivationsYiyou Sun, Chuan Guo, Yixuan LiNeurIPS 2021 · 733 citations
  4. Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?Anna-Kathrin Kopetzki, Bertrand Charpentier, Daniel Zügner, Sandhya Giri et al.ICML 2021 · 55 citations
  5. Fast Decision Boundary based Out-of-Distribution DetectorLitian Liu, Yao QinICML 2024 · 47 citations

Related papers

  1. Leveraging Perturbation Robustness to Enhance Out-of-Distribution DetectionWenxi Chen, Raymond A. Yeh, Shaoshuai Mou, Yan GuCVPR 2025
  2. Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized EmbeddingsHossein Mirzaei, Mackenzie W. MathisICLR 2025
  3. Detection as Regression: Certified Object Detection with Median SmoothingPing-yeh Chiang, Michael J. Curry, Ahmed Abdelkader, Aounon Kumar et al.NeurIPS 2020 · 15 citations
  4. Your Out-of-Distribution Detection Method is Not Robust!Mohammad Azizmalayeri, Arshia Soltani Moakhar, Arman Zarei, Reihaneh Zohrabi et al.NeurIPS 2022 · 29 citations
  5. GEN: Pushing the Limits of Softmax-Based Out-of-Distribution DetectionXixi Liu, Yaroslava Lochman, Christopher ZachCVPR 2023
Dusk over the sea between two cliffs drawn in fine vertical lines