REED: Post-Training Representation Editing for Cross-Domain Linguistic Steganalysis

• URL: http://arxiv.org/abs/2605.28298v1
• Date: Wed, 27 May 2026 10:49:33 GMT
• Title: REED: Post-Training Representation Editing for Cross-Domain Linguistic Steganalysis
• Abstract summary: We propose a post-training representation editing method for cross-domain linguistic steganalysis.<n>The proposed method can achieve high cross-domain detection performance, especially in terms of F1-score.
• Score: 5.68677425690645
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In real-world scenarios of linguistic steganalysis, tested texts usually come from unseen domains with different vocabularies, topics, writing styles, and steganographic generation patterns, which can significantly degrade the detection performance. Although existing cross-domain steganalysis methods can effectively alleviate this problem through distribution alignment, domain-invariant feature learning, etc., the detection performance is not satisfactory. In this paper, we propose a post-training representation editing method for cross-domain linguistic steganalysis. Specifically, the detector is first trained on source-domain data, and then the feature extractor and classifier are kept frozen, and the intermediate representations are deterministically edited before classification. For domain adaptation, we construct a domain-offset vector from marginal source and target representations. For domain generalization, we derive a source-domain cover-to-stego direction to guide sample-specific editing. Experimental results show that compared with the advanced methods, the proposed method can achieve high cross-domain detection performance, especially in terms of F1-score, while requiring no architecture modification or parameter updates after source-domain training.

Related papers

• LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation [43.56251979741165]
  Domain Generalization Semantic (DGSS) focuses on generalizing knowledge from labeled source domains to unseen target domains.<n>Style randomization distorts the underlying feature manifold due to its coarse-grained nature.<n>Feature normalization suppresses discnative, domain-sensitive semantic details owing to its rigid design.
  arXiv  Detail & Related papers  (2026-08-09T16:43:04Z)
• LAB-Det: Language as a Domain-Invariant Bridge for Training-Free One-Shot Domain Generalization in Object Detection [53.988759250627425]
  We introduce training-free one-shot domain generalization for object detection.<n>We project each exemplar into a descriptive text that conditions and guides a frozen detector.<n>We evaluate on UODD (underwater) and NEU-DET (industrial defects)
  arXiv  Detail & Related papers  (2026-02-06T08:03:04Z)
• Cross-Domain Object Detection Using Unsupervised Image Translation [39.857749360034916]
  We propose a method to generate an artificial dataset in the target domain to train an object detector.<n>Our key contributions are the proposal of a less complex yet more effective method that also has an improved interpretability.
  arXiv  Detail & Related papers  (2026-01-16T21:02:42Z)
• Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts [56.57141696245328]
  In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety. Existing methods often struggle to distinguish between domain-level and semantic-level distribution shifts.
  arXiv  Detail & Related papers  (2024-11-06T11:03:02Z)
• Pseudo-label Based Domain Adaptation for Zero-Shot Text Steganalysis [10.587545153412314]
  Cross-domain stego-text analysis method (PDTS) based on pseudo-labeling and domain adaptation (unsupervised learning) We train the model using labeled source domain data and adapt it to target domain data distribution using pseudo-labels for unlabeled target domain data through self-training. Experimental results demonstrate that our method performs well in zero-shot text steganalysis tasks, achieving high detection accuracy even in the absence of labeled data in the target domain, and outperforms current zero-shot text steganalysis methods.
  arXiv  Detail & Related papers  (2024-06-01T04:19:07Z)
• Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification [68.06496970320595]
  Cross-domain sentiment classification (CDSC) aims to use the transferable semantics learned from the source domain to predict the sentiment of reviews in the unlabeled target domain. We present Graph Adaptive Semantic Transfer (GAST) model, an adaptive syntactic graph embedding method that is able to learn domain-invariant semantics from both word sequences and syntactic graphs.
  arXiv  Detail & Related papers  (2022-05-18T07:47:01Z)
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection [90.18752912204778]
  Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
  arXiv  Detail & Related papers  (2021-06-10T05:01:20Z)
• Robust Domain-Free Domain Generalization with Class-aware Alignment [4.442096198968069]
  Domain-Free Domain Generalization (DFDG) is a model-agnostic method to achieve better generalization performance on the unseen test domain. DFDG uses novel strategies to learn domain-invariant class-discriminative features. It obtains competitive performance on both time series sensor and image classification public datasets.
  arXiv  Detail & Related papers  (2021-02-17T17:46:06Z)
• Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment [11.74643883335152]
  Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a target domain. We propose distance metric guided feature alignment (MetFA) to extract discriminative as well as domain-invariant features on both source and target domains. Our model integrates class distribution alignment to transfer semantic knowledge from a source domain to a target domain.
  arXiv  Detail & Related papers  (2020-08-19T13:36:57Z)
• Cross-domain Detection via Graph-induced Prototype Alignment [114.8952035552862]
  We propose a Graph-induced Prototype Alignment (GPA) framework to seek for category-level domain alignment. In addition, in order to alleviate the negative effect of class-imbalance on domain adaptation, we design a Class-reweighted Contrastive Loss. Our approach outperforms existing methods with a remarkable margin.
  arXiv  Detail & Related papers  (2020-03-28T17:46:55Z)
• Towards Fair Cross-Domain Adaptation via Generative Learning [50.76694500782927]
  Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions. We develop a novel Generative Few-shot Cross-domain Adaptation (GFCA) algorithm for fair cross-domain classification.
  arXiv  Detail & Related papers  (2020-03-04T23:25:09Z)
• Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation [13.163271874039191]
  We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their effectiveness on minimizing domain discrepancy via marginal feature distributions alignment. We propose Forward-Backward Cyclic Adaptation, which iteratively computes adaptation from source to target via backward hopping and from target to source via forward passing.
  arXiv  Detail & Related papers  (2020-02-03T06:24:58Z)

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.