{"slug": "causadv-a-causal-based-framework-for-detecting-adversarial-examples", "title": "CausAdv: A Causal-based Framework for Detecting Adversarial Examples", "summary": "Researchers propose CausAdv, a causal framework for detecting adversarial examples in convolutional neural networks (CNNs) by learning causal and non-causal features and quantifying counterfactual information (CI) per filter. The framework improves adversarial detection without a separate detector, as adversarial examples show different CI distributions than clean samples. Code is available on GitHub.", "body_md": "arXiv:2411.00839v4 Announce Type: replace-cross\nAbstract: Deep learning has led to tremendous success in computer vision, largely due to Convolutional Neural Networks (CNNs). However, CNNs have been shown to be vulnerable to crafted adversarial perturbations. This vulnerability of adversarial examples has has motivated research into improving model robustness through adversarial detection and defense methods. In this paper, we address the adversarial robustness of CNNs through causal reasoning. We propose CausAdv: a causal framework for detecting adversarial examples based on counterfactual reasoning. CausAdv learns both causal and non-causal features of every input, and quantifies the counterfactual information (CI) of every filter of the last convolutional layer. We then perform a statistical analysis of the filters' CI across clean and adversarial samples, to demonstrate that adversarial examples exhibit different CI distributions compared to clean samples. Our results show that causal reasoning enhances the process of adversarial detection without the need to train a separate detector. Moreover, we illustrate the efficiency of causal explanations as a helpful detection tool by visualizing the extracted causal features. Code for reproducing our results is available at: https://github.com/HichemDebbi/CausAdv/tree/main.", "url": "https://wpnews.pro/news/causadv-a-causal-based-framework-for-detecting-adversarial-examples", "canonical_source": "https://www.machinebrief.com/news/causadv-a-causal-based-framework-for-detecting-adversarial-e-tgou", "published_at": "2026-07-28 04:00:00+00:00", "updated_at": "2026-07-28 05:57:16.102191+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "ai-safety", "ai-research"], "entities": ["CausAdv", "Convolutional Neural Networks (CNNs)", "arXiv", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/causadv-a-causal-based-framework-for-detecting-adversarial-examples", "markdown": "https://wpnews.pro/news/causadv-a-causal-based-framework-for-detecting-adversarial-examples.md", "text": "https://wpnews.pro/news/causadv-a-causal-based-framework-for-detecting-adversarial-examples.txt", "jsonld": "https://wpnews.pro/news/causadv-a-causal-based-framework-for-detecting-adversarial-examples.jsonld"}}