Aims & Scope

Image and Vision Computing has as a primary aim the provision of an effective medium of interchange for the results of high quality theoretical and applied research fundamental to all aspects of image interpretation and computer vision. The journal publishes work that proposes new image interpretation and computer vision methodology or addresses the application of such methods to real world scenes. It seeks to strengthen a deeper understanding in the discipline by encouraging the quantitative comparison and performance evaluation of the proposed methodology. The coverage includes: image interpretation, scene modelling, object recognition and tracking, shape analysis, monitoring and surveillance, active vision and robotic systems, SLAM, biologically-inspired computer vision, motion analysis, stereo vision, document image understanding, character and handwritten text recognition, face and gesture recognition, biometrics, vision-based human-computer interaction, human activity and behavior understanding, data fusion from multiple sensor inputs, image databases.

In addition to regular manuscripts, Image and Vision Computing Journal solicits manuscripts for the Opinions Column, aimed at initiating a free forum for vision researchers to express their opinions on past, current, or future successes and challenges in research and the community.

An opinion paper should be succinct and focused on a particular topic. Addressing multiple related topics is also possible if this helps making the point. While posing questions helps raising awareness about certain issues, ideally, an opinion paper should also suggest a concrete direction how to address the issues. Topics of interest include, but are not limited to:

    Comments on success and challenges in a (sub-) field of computer vision,
    Remarks on new frontiers in computer vision
    Observations on current practices and trends in research, and suggestions for overcoming unsatisfying aspects
    Observations on current practices and trends in the community regarding, e.g., reviewing process, organizing conferences, how journals are run, and suggestions for overcoming unsatisfying aspects
    Reviews of early seminal work that may have fallen out of fashion
    Summaries of the evolution of one's line of research
    Recommendations for educating new generations of vision researchers.

The format of an opinion paper should comply with the existing formatting guidelines for the Image and Vision Computing Journal submissions, and should not exceed 2 pages.

Months of publication: January/February, March, April, May, June, July/August, September, October, November and December.

Special Issue on Security-AI: Attacks on AI Systems in Computer Vision
Día de Entrega: 2026-04-15

The integration of artificial intelligence (AI) into vision systems has led to unprecedented advancements in automated perception, decision-making, and pattern recognition. However, as deep learning (DL) models become more sophisticated, they also face growing security challenges. Adversarial attacks, data poisoning, and model manipulation expose DL models to subtle yet powerful perturbations, raising concerns about their trustworthiness, resilience, and robustness in complex environments. DL models learn from data distributions and latent patterns. This characteristic makes them particularly susceptible to manipulative attacks that exploit statistical dependencies. Adversarial threats exploit statistical dependencies by introducing imperceptible input perturbations, leading to misclassification and unintended behaviours. Meanwhile, data poisoning infiltrates training datasets, embedding silent vulnerabilities that remain dormant until triggered, complicating AI security. Beyond direct attacks, the increasing complexity of vision models raises critical concerns about interpretability and explainability in adversarial settings, making it essential to understand why and how models fail under attack.This special issue consolidates research at the intersection of adversarial learning, AI security, and robust vision models. By bringing together novel attack strategies, defense mechanisms, and theoretical insights, it seeks to advance the understanding of adversarial robustness and secure AI-driven vision architectures. We invite contributions on theoretical foundations, algorithmic innovations, and emerging defense paradigms shaping the future of secure AI vision systems.

Topics of interests include, but are not limited to:

    Gradient-based attacks on image classifiers
    Adversarial training against gradient-based attacks
    Black-box and white-box adversarial attack strategies in computer vision tasks
    Robustness evaluation of AI-based image analysis models under adversarial conditions
    Poisoning attacks in Federated Learning (FL) for computer vision applications
    Secure aggregation and privacy-preserving techniques in FL for vision-based AI
    Backdoor attacks and trojaned models in facial recognition, DeepFake detection, and medical imaging
    Detecting and filtering poisoned data in large-scale image datasets
    Evasion attacks against AI-based image forensics and deepfake detection
    AI security in autonomous vehicle perception systems
    Explainability and interpretability of adversarial robustness in vision models
    Adversarial perturbations in AI-driven deepfake detection systems

Guest editors:

Matteo Polsinelli, PhD
University of Salerno, Fisciano, Italy
Email: mpolsinelli@unisa.it

Lucia Cimmino, PhD
University of Salerno, Fisciano, Italy
Email: lcimmino@unisa.it

Javier Lorenzo-Navarro, PhD
University of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain
Email: javier.lorenzo@ulpgc.es

Oliverio J. Santana Jaria, PhD
University of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain
Email: oliverio.santana@ulpgc.es

Manuscript submission information:

The Journal's submission system (Editorial Manager) will be open for submissions to our Special Issue from December 15, 2025. Please refer to the Guide for Authors to prepare your manuscript and select the article type of “VSI: Security-AI” when submitting your manuscript online. Both the Guide for Authors and the submission portal could be found on the Journal Homepage: Guide for authors - Image and Vision Computing - ISSN 0262-8856 (elsevier.com). 

Important Dates:

Submission Open Date: December 15th, 2025
Final Manuscript Submission Deadline: April 15th, 2026
Editorial Acceptance Deadline: June 15th, 2026

Keywords:

    Adversarial Attacks in Computer Vision
    Robust and Secure Deep Learning Models
    Data Poisoning and Backdoor Threats
    Trustworthy Deep Vision Systems