DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation

• URL: http://arxiv.org/abs/2607.00183v1
• Date: Tue, 30 Jun 2026 20:57:51 GMT
• Title: DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation
• Abstract summary: Adapting pre-trained text-to-image diffusion models, whether to learn new visual concepts or erase unwanted ones, is routinely evaluated on its intended effects alone.<n>We demonstrate that adaptation systematically damages semantically unrelated concepts in ways that aggregate metrics structurally cannot surface.<n>We introduce DriftScope, a prompt-level diagnostic tool that takes any two model checkpoints and returns a ranked list of tokens whose visual concepts have shifted most between them.
• Score: 50.584834483403675
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adapting pre-trained text-to-image diffusion models, whether to learn new visual concepts or erase unwanted ones, is routinely evaluated on its intended effects alone. We argue this framing is incomplete. Through sparse autoencoder analysis and zero-shot classification, we demonstrate that adaptation systematically damages semantically unrelated concepts in ways that aggregate metrics structurally cannot surface: when damage is severe enough for FID and KID to respond, the model is already nearly unusable; when the model remains functional, FID and KID stay flat while specific classes silently suffer worst-case zero-shot accuracy drops of up to 18.9 points and concept-level distributions shift dramatically. This pattern appears at both ends of the adaptation spectrum (concept customization and concept unlearning), suggesting it is a systematic consequence of weight-level modification rather than an artifact of any particular method. To surface this hidden drift before deployment, we introduce DriftScope, a prompt-level diagnostic tool that takes any two model checkpoints and returns a ranked list of tokens whose visual concepts have shifted most between them. DriftScope optimizes a soft prompt to attribute drift at the token level without requiring access to real data or model internals. The result is an interpretable, concept-level audit that aggregate evaluation cannot provide.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Cluster Analysis and Concept Drift Detection in Malware [1.3812010983144798]
  Concept drift refers to gradual or sudden changes in the properties of data that affect the accuracy of machine learning models.<n>We propose and analyze a clustering-based approach to detecting concept drift in the malware domain.
  arXiv  Detail & Related papers  (2025-02-19T22:42:30Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• A Neighbor-Searching Discrepancy-based Drift Detection Scheme for Learning Evolving Data [40.00357483768265]
  This work presents a novel real concept drift detection method based on Neighbor-Searching Discrepancy. The proposed method is able to detect real concept drift with high accuracy while ignoring virtual drift. It can also indicate the direction of the classification boundary change by identifying the invasion or retreat of a certain class.
  arXiv  Detail & Related papers  (2024-05-23T04:03:36Z)
• Combating Concept Drift with Explanatory Detection and Adaptation for Android Malware Classification [17.399454244765842]
  DREAM is a novel system that improves drift detection and establishes an explanatory adaptation process.<n>Our evaluation shows that DREAM effectively improves the drift detection accuracy and reduces the expert analysis effort in adaptation.
  arXiv  Detail & Related papers  (2024-05-07T07:55:45Z)
• CADM: Confusion Model-based Detection Method for Real-drift in Chunk Data Stream [3.0885191226198785]
  Concept drift detection has attracted considerable attention due to its importance in many real-world applications such as health monitoring and fault diagnosis. We propose a new approach to detect real-drift in the chunk data stream with limited annotations based on concept confusion.
  arXiv  Detail & Related papers  (2023-03-25T08:59:27Z)
• Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection [64.65563422852568]
  We improve the challenging monocular 3D object detection problem with a general semi-supervised framework. We introduce a novel, simple, yet effective Augment and Criticize' framework that explores abundant informative samples from unlabeled data. The two new detectors, dubbed 3DSeMo_DLE and 3DSeMo_FLEX, achieve state-of-the-art results with remarkable improvements for over 3.5% AP_3D/BEV (Easy) on KITTI.
  arXiv  Detail & Related papers  (2023-03-20T16:28:15Z)
• Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent [97.64313409741614]
  We propose to enforce a emphconsistency property which states that predictions of the model on its own generated data are consistent across time. We show that our novel training objective yields state-of-the-art results for conditional and unconditional generation in CIFAR-10 and baseline improvements in AFHQ and FFHQ.
  arXiv  Detail & Related papers  (2023-02-17T18:45:04Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Detecting Concept Drift With Neural Network Model Uncertainty [0.0]
  Uncertainty Drift Detection (UDD) is able to detect drifts without access to true labels. In contrast to input data-based drift detection, our approach considers the effects of the current input data on the properties of the prediction model. We show that UDD outperforms other state-of-the-art strategies on two synthetic as well as ten real-world data sets for both regression and classification tasks.
  arXiv  Detail & Related papers  (2021-07-05T08:56:36Z)

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.