Trustworthy Deep Learning in Practice
A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".
Deadline for manuscript submissions: 15 November 2024 | Viewed by 121
Special Issue Editors
Interests: trustworthy AI in multimodal (e.g., adversarial examples/physical adversarial attacks/adversarial defense/backdoor detection/deepfake detection)
Interests: AI safety and security, with broad interests in the areas of adversarial examples; backdoor attacks; interpretable deep learning; model robustness; fairness testing; AI testing and evaluation
Interests: fast visual computing (e.g., large-scale search/understanding) and robust deep learning (e.g., network quantization, adversarial attack/defense, few shot learning)
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Recently, deep learning has achieved remarkable performance across a wide range of applications, including computer vision, natural language processing, and acoustics. However, research has revealed severe security challenges over the deep learning life-cycle, prompting concern about their trustworthiness in practice. Since there are potential risks that threaten the applications of deep learning in both the digital and physical world, it is necessary to converge advanced investigations in correlated research areas to successfully diagnose model blind-spots and further understand, and improve, deep learning systems in practice.
In this Special Issue, we aim to bring together researchers from the fields of adversarial machine learning, model robustness, model privacy, and explainable AI to discuss recent research and future directions for trustworthy AI. We invite submissions on any aspect of trustworthiness in practical deep learning systems (in particular computer vision and pattern recognition). We welcome research contributions related to the following (but not limited to) topics:
- Adversarial learning (attacks, defenses);
- Backdoor attacks and mitigations for deep learning models;
- Model stealing for AI applications and systems;
- Deepfake techniques on images and videos;
- Stable learning and model generalization;
- Robustness, fairness, privacy, and reliability in AI;
- Explainable and practical AI.
Dr. Jiakai Wang
Dr. Aishan Liu
Prof. Dr. Xianglong Liu
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- trustworthy AI
- adversarial learning
- stable learning
- practical learning
