Learning Counterfactually Decoupled Attention for Open-World Model Attribution

• URL: http://arxiv.org/abs/2506.23074v1
• Date: Sun, 29 Jun 2025 03:25:45 GMT
• Title: Learning Counterfactually Decoupled Attention for Open-World Model Attribution
• Authors: Yu Zheng, Boyang Gong, Fanye Kong, Yueqi Duan, Bingyao Yu, Wenzhao Zheng, Lei Chen, Jiwen Lu, Jie Zhou,
• Abstract summary: We propose a Counterfactually Decoupled Attention Learning (CDAL) method for open-world model attribution.<n>Our method consistently improves state-of-the-art models by large margins, particularly for unseen novel attacks.
• Score: 75.52873383916672
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose a Counterfactually Decoupled Attention Learning (CDAL) method for open-world model attribution. Existing methods rely on handcrafted design of region partitioning or feature space, which could be confounded by the spurious statistical correlations and struggle with novel attacks in open-world scenarios. To address this, CDAL explicitly models the causal relationships between the attentional visual traces and source model attribution, and counterfactually decouples the discriminative model-specific artifacts from confounding source biases for comparison. In this way, the resulting causal effect provides a quantification on the quality of learned attention maps, thus encouraging the network to capture essential generation patterns that generalize to unseen source models by maximizing the effect. Extensive experiments on existing open-world model attribution benchmarks show that with minimal computational overhead, our method consistently improves state-of-the-art models by large margins, particularly for unseen novel attacks. Source code: https://github.com/yzheng97/CDAL.

Related papers

• Zero-Shot Image Anomaly Detection Using Generative Foundation Models [2.241618130319058]
  This research explores the use of score-based generative models as foundational tools for semantic anomaly detection.<n>By analyzing Stein score errors, we introduce a novel method for identifying anomalous samples without requiring re-training on each target dataset.<n>Our approach improves over state-of-the-art and relies on training a single model on one dataset -- CelebA -- which we find to be an effective base distribution.
  arXiv  Detail & Related papers  (2025-07-30T13:56:36Z)
• Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization [25.181305392387802]
  Attribute bias in federated learning (FL) typically leads local models to optimize inconsistently due to the learning of non-causal associations.<n>We propose the underlineFederated underlineDeconfounding and underlineDebiasing underlineLearning (FedDDL) method.<n>It constructs a structured causal graph to analyze the model inference process, and performs backdoor adjustment to eliminate confounding paths.
  arXiv  Detail & Related papers  (2025-05-08T06:32:59Z)
• Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing [15.214861534330236]
  We introduce Diffusing DeBias (DDB) as a plug-in for common methods of unsupervised model debiasing.<n>Specifically, our approach adopts conditional diffusion models to generate synthetic bias-aligned images.<n>By tackling the fundamental issue of bias-conflicting training samples in learning auxiliary models, our proposed method beats current state-of-the-art in multiple benchmark datasets.
  arXiv  Detail & Related papers  (2025-02-13T18:17:03Z)
• High-Performance Few-Shot Segmentation with Foundation Models: An Empirical Study [64.06777376676513]
  We develop a few-shot segmentation (FSS) framework based on foundation models. To be specific, we propose a simple approach to extract implicit knowledge from foundation models to construct coarse correspondence. Experiments on two widely used datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-09-10T08:04:11Z)
• Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models [54.132297393662654]
  We introduce a hybrid method that fine-tunes cutting-edge diffusion models by optimizing reward models through RL. We demonstrate the capability of our approach to outperform the best designs in offline data, leveraging the extrapolation capabilities of reward models.
  arXiv  Detail & Related papers  (2024-05-30T03:57:29Z)
• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• Improving Generative Model-based Unfolding with Schr\"{o}dinger Bridges [14.989614554242229]
  Machine learning-based unfolding has enabled unbinned and high-dimensional differential cross section measurements. We propose to use Schroedinger Bridges and diffusion models to create SBUnfold, an unfolding approach that combines the strengths of both discriminative and generative models. We show that SBUnfold achieves excellent performance compared to state of the art methods on a synthetic Z+jets dataset.
  arXiv  Detail & Related papers  (2023-08-23T18:01:01Z)
• Studying How to Efficiently and Effectively Guide Models with Explanations [52.498055901649025]
  'Model guidance' is the idea of regularizing the models' explanations to ensure that they are "right for the right reasons" We conduct an in-depth evaluation across various loss functions, attribution methods, models, and 'guidance depths' on the PASCAL VOC 2007 and MS COCO 2014 datasets. Specifically, we guide the models via bounding box annotations, which are much cheaper to obtain than the commonly used segmentation masks.
  arXiv  Detail & Related papers  (2023-03-21T15:34:50Z)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• De-Biasing Generative Models using Counterfactual Methods [0.0]
  We propose a new decoder based framework named the Causal Counterfactual Generative Model (CCGM) Our proposed method combines a causal latent space VAE model with specific modification to emphasize causal fidelity. We explore how better disentanglement of causal learning and encoding/decoding generates higher causal intervention quality.
  arXiv  Detail & Related papers  (2022-07-04T16:53:20Z)

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.