When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations

• URL: http://arxiv.org/abs/2606.16196v2
• Date: Sun, 21 Jun 2026 13:48:28 GMT
• Title: When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations
• Abstract summary: We propose an interpretable OOD detection framework that probes the stability of model predictions under class-conditioned semantic perturbations.<n>By framing OOD detection as a concept conditioned stability analysis, our approach provides both a discriminative OOD signal and an interpretable lens into the internal mechanisms driving model uncertainty.
• Score: 6.4945321478117455
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks have achieved remarkable performance across medical imaging tasks, yet their tendency to overgeneralize under distributional shifts poses a major obstacle to safe clinical deployment. Out-of-Distribution (OOD) detection methods aim to mitigate this risk, but most existing approaches rely on opaque internal signals with poorly understood semantic meaning, limiting trust in safety-critical settings. In this work, we propose an interpretable OOD detection framework that probes the stability of model predictions under class-conditioned semantic perturbations. Leveraging sparse autoencoders (SAEs), we learn class-specific concept vectors from in-distribution data that disentangle dense intermediate representations into sparse, semantically meaningful components. At inference, we perturb deeper-layer representations using the concept vectors associated with the model's predicted class and measure the class logits stability. We hypothesize that in-distribution samples exhibit low sensitivity to such perturbations, as their representations align with class-specific semantic directions, whereas OOD samples show amplified deviations due to representational misalignment. By framing OOD detection as a concept conditioned stability analysis, our approach provides both a discriminative OOD signal and an interpretable lens into the internal mechanisms driving model uncertainty, making it particularly suitable for high stakes medical applications.

Related papers

• Empirical Analysis of Adversarial Robustness and Explainability Drift in Cybersecurity Classifiers [0.0]
  This paper presents an empirical study of adversarial robustness and explainability drift across two cybersecurity domains.<n>We introduce a quantitative metric, the Robustness Index (RI), defined as the area under the accuracy perturbation curve.<n>Experiments on the Phishing Websites and NB15 datasets show consistent robustness trends, with adversarial training improving RI by up to 9 percent while maintaining clean-data accuracy.
  arXiv  Detail & Related papers  (2026-02-06T05:30:37Z)
• Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence [36.624406746797085]
  Singularities in semi-discrete optimal transport (OT) mark regions of semantic ambiguity.<n>We propose a principled framework to mitigate OOD overconfidence by leveraging the geometry of OT-induced singular boundaries.<n>Our method significantly alleviates OOD overconfidence and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-01-29T06:29:36Z)
• General OOD Detection via Model-aware and Subspace-aware Variable Priority [1.293838707857305]
  Out-of-distribution (OOD) detection is essential for determining when a supervised model encounters inputs that differ meaningfully from its training distribution.<n>We introduce a framework for OOD detection that is simultaneously model aware and subspace aware, and that embeds variable prioritization directly into the detection step.
  arXiv  Detail & Related papers  (2025-12-15T05:55:35Z)
• Secure Diagnostics: Adversarial Robustness Meets Clinical Interpretability [9.522045116604358]
  Deep neural networks for medical image classification often fail to generalize consistently in clinical practice.<n>This paper examines interpretability in deep neural networks fine-tuned for fracture detection by evaluating model performance against adversarial attack.
  arXiv  Detail & Related papers  (2025-04-07T20:26:02Z)
• Semantic or Covariate? A Study on the Intractable Case of Out-of-Distribution Detection [70.57120710151105]
  We provide a more precise definition of the Semantic Space for the ID distribution. We also define the "Tractable OOD" setting which ensures the distinguishability of OOD and ID distributions.
  arXiv  Detail & Related papers  (2024-11-18T03:09:39Z)
• Free Lunch for Generating Effective Outlier Supervision [46.37464572099351]
  We propose an ultra-effective method to generate near-realistic outlier supervision. Our proposed textttBayesAug significantly reduces the false positive rate over 12.50% compared with the previous schemes.
  arXiv  Detail & Related papers  (2023-01-17T01:46:45Z)
• Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection [67.49587673594276]
  We introduce a new perceptron bias assumption that suggests discriminator models are more sensitive to certain features of the input, leading to the overconfidence problem. We demonstrate that the diffusion denoising process (DDP) of DMs serves as a novel form of asymmetric, which is well-suited to enhance the input and mitigate the overconfidence problem. Our experiments on CIFAR10, CIFAR100, and ImageNet show that our method outperforms SOTA approaches.
  arXiv  Detail & Related papers  (2022-11-21T08:45:08Z)
• On the Practicality of Deterministic Epistemic Uncertainty [106.06571981780591]
  deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution data. It remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications.
  arXiv  Detail & Related papers  (2021-07-01T17:59:07Z)
• Provably Robust Detection of Out-of-distribution Data (almost) for free [124.14121487542613]
  Deep neural networks are known to produce highly overconfident predictions on out-of-distribution (OOD) data. In this paper we propose a novel method where from first principles we combine a certifiable OOD detector with a standard classifier into an OOD aware classifier. In this way we achieve the best of two worlds: certifiably adversarially robust OOD detection, even for OOD samples close to the in-distribution, without loss in prediction accuracy and close to state-of-the-art OOD detection performance for non-manipulated OOD data.
  arXiv  Detail & Related papers  (2021-06-08T11:40:49Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)
• The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
  The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
  arXiv  Detail & Related papers  (2020-12-05T17:30:35Z)
• Robust Out-of-distribution Detection for Neural Networks [51.19164318924997]
  We show that existing detection mechanisms can be extremely brittle when evaluating on in-distribution and OOD inputs. We propose an effective algorithm called ALOE, which performs robust training by exposing the model to both adversarially crafted inlier and outlier examples.
  arXiv  Detail & Related papers  (2020-03-21T17:46:28Z)

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.