Overview
The International Workshop on Understanding and Harnessing AdVersarial Examples (U-HAVE 2019) is set to take place in conjunction with the IEEE International Conference on Data Mining (ICDM 2019). This workshop aims to create a platform for researchers and professionals to discuss the latest advancements in adversarial examples, which are crucial in enhancing the robustness of machine learning models.
Background & Relevance
Adversarial examples are inputs to machine learning models that have been intentionally modified to cause the model to make a mistake. These subtle alterations can significantly impact the performance of state-of-the-art models, making the study of adversarial examples a vital area in machine learning and data mining. Understanding these examples can lead to improved defenses and innovative applications, making this workshop particularly relevant for those in the field.
Key Details
- Event: U-HAVE 2019 Workshop
- Date: November 8-11, 2019
- Location: Beijing, China
- Submission Deadline: August 20, 2019
- Notification of Acceptance: September 4, 2019
- Camera-Ready Submission: September 8, 2019
- Link for Submission: Submit Here
Eligibility & Participation
The workshop invites contributions from researchers, practitioners, and technologists interested in adversarial examples and their implications in machine learning and data mining. It is an excellent opportunity for those looking to share their findings and engage with others in the community.
Submission or Application Guidelines
Participants are encouraged to submit their papers by selecting the U-HAVE workshop during the submission process. The papers will undergo a review process, and selected works will be published in the ICDM workshop proceedings, with opportunities for further publication in ISI-indexed journals.
Additional Context / Real-World Relevance
The implications of adversarial examples extend beyond theoretical research; they have practical applications in various domains, including business data security, medical informatics, and decision-making processes. By exploring adversarial examples, researchers can contribute to the development of more secure and reliable machine learning systems.
Conclusion
This workshop presents a valuable opportunity for those involved in machine learning and data mining to delve into the complexities of adversarial examples. Researchers are encouraged to submit their work and participate in discussions that could shape the future of this critical area in AI. Explore the potential of adversarial examples and contribute to advancing the field by submitting your papers to U-HAVE 2019.
Category: CFP & Deadlines
Tags: adversarial examples, machine learning, data mining, deep learning, IEEE ICDM, workshop, robustness, data security, generative adversarial networks
