Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities

• URL: http://arxiv.org/abs/2512.18651v1
• Date: Sun, 21 Dec 2025 08:55:56 GMT
• Title: Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities
• Authors: Zhiyuan Peng, Zihan Ye, Shreyank N Gowda, Yuping Yan, Haotian Xu, Ling Shao,
• Abstract summary: Zero-shot Learning (ZSL) aims to enable image classifiers to recognize images from unseen classes that were not included during training.<n>While ZSL models promise to improve generalization and interpretability, their robustness under systematic input perturbations remain unclear.<n>We present an empirical analysis about the robustness of existing ZSL methods at both classlevel and concept-level.
• Score: 38.00830507239569
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Zero-shot Learning (ZSL) aims to enable image classifiers to recognize images from unseen classes that were not included during training. Unlike traditional supervised classification, ZSL typically relies on learning a mapping from visual features to predefined, human-understandable class concepts. While ZSL models promise to improve generalization and interpretability, their robustness under systematic input perturbations remain unclear. In this study, we present an empirical analysis about the robustness of existing ZSL methods at both classlevel and concept-level. Specifically, we successfully disrupted their class prediction by the well-known non-target class attack (clsA). However, in the Generalized Zero-shot Learning (GZSL) setting, we observe that the success of clsA is only at the original best-calibrated point. After the attack, the optimal bestcalibration point shifts, and ZSL models maintain relatively strong performance at other calibration points, indicating that clsA results in a spurious attack success in the GZSL. To address this, we propose the Class-Bias Enhanced Attack (CBEA), which completely eliminates GZSL accuracy across all calibrated points by enhancing the gap between seen and unseen class probabilities.Next, at concept-level attack, we introduce two novel attack modes: Class-Preserving Concept Attack (CPconA) and NonClass-Preserving Concept Attack (NCPconA). Our extensive experiments evaluate three typical ZSL models across various architectures from the past three years and reveal that ZSL models are vulnerable not only to the traditional class attack but also to concept-based attacks. These attacks allow malicious actors to easily manipulate class predictions by erasing or introducing concepts. Our findings highlight a significant performance gap between existing approaches, emphasizing the need for improved adversarial robustness in current ZSL models.

Related papers

• Uncertainty-guided Boundary Learning for Imbalanced Social Event Detection [64.4350027428928]
  We propose a novel uncertainty-guided class imbalance learning framework for imbalanced social event detection tasks. Our model significantly improves social event representation and classification tasks in almost all classes, especially those uncertain ones.
  arXiv  Detail & Related papers  (2023-10-30T03:32:04Z)
• Improving Performance of Semi-Supervised Learning by Adversarial Attacks [1.675857332621569]
  We present a generalized framework, named SCAR, for improving the performance of recent SSL algorithms. By adversarially attacking pre-trained models with semi-supervision, our framework shows substantial advances in classifying images.
  arXiv  Detail & Related papers  (2023-08-08T03:29:43Z)
• Zero-Shot Learning by Harnessing Adversarial Samples [52.09717785644816]
  We propose a novel Zero-Shot Learning (ZSL) approach by Harnessing Adversarial Samples (HAS) HAS advances ZSL through adversarial training which takes into account three crucial aspects. We demonstrate the effectiveness of our adversarial samples approach in both ZSL and Generalized Zero-Shot Learning (GZSL) scenarios.
  arXiv  Detail & Related papers  (2023-08-01T06:19:13Z)
• Effective Targeted Attacks for Adversarial Self-Supervised Learning [58.14233572578723]
  unsupervised adversarial training (AT) has been highlighted as a means of achieving robustness in models without any label information. We propose a novel positive mining for targeted adversarial attack to generate effective adversaries for adversarial SSL frameworks. Our method demonstrates significant enhancements in robustness when applied to non-contrastive SSL frameworks, and less but consistent robustness improvements with contrastive SSL frameworks.
  arXiv  Detail & Related papers  (2022-10-19T11:43:39Z)
• Federated Zero-Shot Learning for Visual Recognition [55.65879596326147]
  We propose a novel Federated Zero-Shot Learning FedZSL framework. FedZSL learns a central model from the decentralized data residing on edge devices. The effectiveness and robustness of FedZSL are demonstrated by extensive experiments conducted on three zero-shot benchmark datasets.
  arXiv  Detail & Related papers  (2022-09-05T14:49:34Z)
• How Robust are Discriminatively Trained Zero-Shot Learning Models? [9.62543698736491]
  We present novel analyses on the robustness of discriminative ZSL to image corruptions. We release the first ZSL corruption robustness datasets SUN-C, CUB-C and AWA2-C.
  arXiv  Detail & Related papers  (2022-01-26T14:41:10Z)
• Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning [82.07273754143547]
  We propose a meta-continual zero-shot learning (MCZSL) approach to generalizing a model to categories unseen during training. By pairing self-gating of attributes and scaled class normalization with meta-learning based training, we are able to outperform state-of-the-art results.
  arXiv  Detail & Related papers  (2021-02-23T18:36:14Z)
• OntoZSL: Ontology-enhanced Zero-shot Learning [19.87808305218359]
  Key to implementing Zero-shot Learning (ZSL) is to leverage the prior knowledge of classes which builds the semantic relationship between classes. In this paper, we explore richer and more competitive prior knowledge to model the inter-class relationship for ZSL. To address the data imbalance between seen classes and unseen classes, we developed a generative ZSL framework with Generative Adversarial Networks (GANs)
  arXiv  Detail & Related papers  (2021-02-15T04:39:58Z)
• A Deep Dive into Adversarial Robustness in Zero-Shot Learning [9.62543698736491]
  We present a study aimed on evaluating the adversarial robustness of Zero-shot Learning (ZSL) and Generalized Zero-shot Learning (GZSL) models. In addition to creating possibly the first benchmark on adversarial robustness of ZSL models, we also present analyses on important points that require attention for better interpretation of ZSL robustness results.
  arXiv  Detail & Related papers  (2020-08-17T22:26:06Z)

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.