SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense

• URL: http://arxiv.org/abs/2510.08761v1
• Date: Thu, 09 Oct 2025 19:23:19 GMT
• Title: SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense
• Abstract summary: Adversarial attacks significantly challenge the safe deployment of deep learning models, particularly in real-world applications.<n>Traditional defenses often rely on computationally intensive optimization to improve robustness, whereas the human visual system achieves inherent robustness to adversarial perturbations through evolved biological mechanisms.<n>We propose a novel defense framework incorporating three key biological mechanisms: foveal-peripheral processing, saccadic eye movements, and cortical filling-in.
• Score: 9.044690673064236
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Adversarial attacks significantly challenge the safe deployment of deep learning models, particularly in real-world applications. Traditional defenses often rely on computationally intensive optimization (e.g., adversarial training or data augmentation) to improve robustness, whereas the human visual system achieves inherent robustness to adversarial perturbations through evolved biological mechanisms. We hypothesize that attention guided non-homogeneous sparse sampling and predictive coding plays a key role in this robustness. To test this hypothesis, we propose a novel defense framework incorporating three key biological mechanisms: foveal-peripheral processing, saccadic eye movements, and cortical filling-in. Our approach employs reinforcement learning-guided saccades to selectively capture multiple foveal-peripheral glimpses, which are integrated into a reconstructed image before classification. This biologically inspired preprocessing effectively mitigates adversarial noise, preserves semantic integrity, and notably requires no retraining or fine-tuning of downstream classifiers, enabling seamless integration with existing systems. Experiments on the ImageNet dataset demonstrate that our method improves system robustness across diverse classifiers and attack types, while significantly reducing training overhead compared to both biologically and non-biologically inspired defense techniques.

Related papers

• Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective [0.0]
  Machine learning-based malware detectors are increasingly vulnerable to adversarial examples.<n>Traditional defenses, such as one-shot adversarial training, often fail against adaptive attackers who use reinforcement learning to bypass detection.<n>This paper proposes a robust defense framework based on bilevel optimization, explicitly modeling the strategic interaction between a defender and an attacker as an adversarial co-evolutionary process.
  arXiv  Detail & Related papers  (2026-04-24T14:01:18Z)
• Efficient Preemptive Robustification with Image Sharpening [34.002154410494285]
  Deep neural networks rely on high-dimensional, non-robust representations, making them vulnerable to imperceptible perturbations.<n>Recent studies reveal a positive correlation between texture intensity and the robustness of benign samples.<n>We show that image sharpening alone can efficiently robustify images.
  arXiv  Detail & Related papers  (2026-03-26T09:49:33Z)
• Towards Robust Universal Perturbation Attacks: A Float-Coded, Penalty-Driven Evolutionary Approach [10.211523683826004]
  Universal adversarial noise perturbations (UAPs) have garnered significant attention due to their ability to undermine deep neural networks.<n>We introduce a single-objective-driven framework for generating such perturbations.<n>Our framework consistently produces perturbations with smaller sizes, higher misclassification effectiveness, and faster compared to existing methods.
  arXiv  Detail & Related papers  (2026-01-18T23:31:12Z)
• C-LEAD: Contrastive Learning for Enhanced Adversarial Defense [21.31610891219127]
  Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection.<n>They are vulnerable to adversarial attacks, which can cause incorrect predictions with small perturbations in input images.<n>This paper presents a novel approach that utilizes contrastive learning for adversarial defense.
  arXiv  Detail & Related papers  (2025-10-31T07:32:55Z)
• Enhancing Variational Autoencoders with Smooth Robust Latent Encoding [54.74721202894622]
  Variational Autoencoders (VAEs) have played a key role in scaling up diffusion-based generative models.<n>We introduce Smooth Robust Latent VAE, a novel adversarial training framework that boosts both generation quality and robustness.<n>Experiments show that SRL-VAE improves both generation quality, in image reconstruction and text-guided image editing, and robustness, against Nightshade attacks and image editing attacks.
  arXiv  Detail & Related papers  (2025-04-24T03:17:57Z)
• Unleashing the Power of Pre-trained Encoders for Universal Adversarial Attack Detection [21.03032944637112]
  Adrial attacks pose a critical security threat to real-world AI systems.<n>This paper proposes a lightweight adversarial detection framework based on the large-scale pre-trained vision-language model CLIP.
  arXiv  Detail & Related papers  (2025-04-01T05:21:45Z)
• Sustainable Self-evolution Adversarial Training [41.35034408227795]
  We propose a novel Sustainable Self-Evolution Adversarial Training (SSEAT) framework.<n>We introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples.<n>We also propose an adversarial data replay module to better select more diverse and key relearning data.
  arXiv  Detail & Related papers  (2024-12-03T08:41:11Z)
• Protecting Feed-Forward Networks from Adversarial Attacks Using Predictive Coding [0.20718016474717196]
  An adversarial example is a modified input image designed to cause a Machine Learning (ML) model to make a mistake. This study presents a practical and effective solution -- using predictive coding networks (PCnets) as an auxiliary step for adversarial defence.
  arXiv  Detail & Related papers  (2024-10-31T21:38:05Z)
• Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks [0.0]
  Adversarial attacks pose significant threats to the robustness of deep learning models in image classification. This paper explores and refines defense mechanisms against these attacks to enhance the resilience of neural networks.
  arXiv  Detail & Related papers  (2024-08-20T02:00:02Z)
• Mutual-modality Adversarial Attack with Semantic Perturbation [81.66172089175346]
  We propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme. Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.
  arXiv  Detail & Related papers  (2023-12-20T05:06:01Z)
• Blending adversarial training and representation-conditional purification via aggregation improves adversarial robustness [6.484231366444063]
  CARSO is able to defend itself against adaptive end-to-end white-box attacks devised for defences.<n>Our method improves by a significant margin the state-of-the-art for Cifar-10, Cifar-100, and TinyImageNet-200.
  arXiv  Detail & Related papers  (2023-05-25T09:04:31Z)
• Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness [53.094682754683255]
  We propose a Model-Agnostic Meta-Attack (MAMA) approach to discover stronger attack algorithms automatically. Our method learns the in adversarial attacks parameterized by a recurrent neural network. We develop a model-agnostic training algorithm to improve the ability of the learned when attacking unseen defenses.
  arXiv  Detail & Related papers  (2021-10-13T13:54:24Z)
• Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution [83.84968082791444]
  Deep neural networks are vulnerable to intentionally crafted adversarial examples. Various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models.
  arXiv  Detail & Related papers  (2021-08-29T08:11:36Z)
• Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training [106.34722726264522]
  A range of adversarial defense techniques have been proposed to mitigate the interference of adversarial noise. Pre-processing methods may suffer from the robustness degradation effect. A potential cause of this negative effect is that adversarial training examples are static and independent to the pre-processing model. We propose a method called Joint Adversarial Training based Pre-processing (JATP) defense.
  arXiv  Detail & Related papers  (2021-06-10T01:45:32Z)
• Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition [133.35968094967626]
  Skeleton-based action recognition has attracted increasing attention due to its strong adaptability to dynamic circumstances. With the help of deep learning techniques, it has also witnessed substantial progress and currently achieved around 90% accuracy in benign environment. Research on the vulnerability of skeleton-based action recognition under different adversarial settings remains scant.
  arXiv  Detail & Related papers  (2020-05-14T17:12:52Z)

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.