analiza aiqbench
This research introduces CausAdv, a framework that leverages causal reasoning and counterfactual analysis to detect adversarial examples in Convolutional Neural Networks without requiring separate detector models. By quantifying the distribution of counterfactual information across filter outputs, the method distinguishes between clean inputs and crafted perturbations more robustly than traditional approaches. The study highlights how integrating causal explanations can enhance model security directly within existing architectures rather than as an add-on layer.
CausAdv: A Causal-based Framework for Detecting Adversarial Examples
arXiv:2411.00839v4 Announce Type: replace-cross Abstract: 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.
Abstract: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: this https URL.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Methodology (stat.ME); Machine Learning (stat.ML)
arXiv:2411.00839 [cs.LG]
(or arXiv:2411.00839v4 [cs.LG] for this version)
Text integral sub licența deschisă a publicației · 202 cuvinte
Subiecte conexe
How might continual learning affect safety and alignment?
LessWrong · 13 iun. 2026
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · 23 sept. 2026
Amazon is investing in the Lean Focused Research Organization
Amazon Science · 26 iul. 2026
Coverage-driven alignment - What ‘Teaching Claude Why’ can borrow from AV verification
LessWrong · 8 iun. 2026