Aim and Scope

The goal is to build reliable machine learning (ML) models, which are resilient in adversarial settings.

There has been growing interest in rectifying machine learning vulnerabilities and preserve privacy. Adversarial machine learning and privacy-preserving has attracted tremendous attention in the machine learning society over the past few years.  Recent research has studied the vulnerability of machine learning ML algorithms and various defense mechanisms against those vulnerabilities. The questions surrounding this space are more pressing and relevant than ever before: How can we make a system robust to novel or potentially adversarial inputs? How can machine learning systems detect and adapt to changes in the environment over time? When can we trust that a system that has performed well in the past will continue to do so in the future? These questions are essential to consider in designing systems for high stakes applications such as self-driving cars and automated surgical assistants.            

We aim to bring together researchers in diverse areas such as reinforcement learning, human-robot interaction, game theory, cognitive science, and security to further the field of reliable and trustworthy machine learning. We will focus on robustness, trustworthiness, privacy preservation, and scalability. Robustness refers to the ability to withstand the effects of adversaries, including adversarial examples and poisoning data, distributional shift, model misspecification, corrupted data. Trustworthiness is guaranteed by transparency, explainability, and privacy preservation. Scalability refers to the ability to generalize to novel situations and objectives. 

This TF aims to promote the most recent advances of secure machine learning from both the theoretical and empirical perspectives and the novel applications.  

Task Force Chair:

• Simon See, NVIDIA AI Technology Centre, Singapore

Task Force Vice-Chairs:

• Catherine Huang, McAfee, USA

• Yaochu Jin, University of Surrey, UK

Task Force Members:

• Catherine Huang:        McAfee LLC, USA (Catherine_huang@mcafee.com) 

• Yaochu Jin:                       University of Surrey, UK (yaochu.jin@surrey.ac.uk)

• Dipankar Dasgupta:  University of Memphis, USA ( dasgupta@memphis.edu)

• Yew Soon Ong:               Nanyang Technological University, Singapore (ASYSOng@ntu.edu.sg)

• Xinghua Qu:                   Tiktok/Bytedance AI lab, Singapore (xinghua.qu@bytedance.com)

• Xiao Huang:                    HSBC, UK (Huang.xiao@hsbc.com)

• Celeste Fralick:             McAfee LLC, USA (celeste_fralick@mcafee.com)

• Samuel Mulder:            Sandia National Labs, USA ( samulde@sandia.gov)

• Huiyu (Joe) Zhou :        University of Leicester (hz143@leicester.ac.uk )

• Serena Zhang:           Facebook, USA (serenazhang@fb.com )

• Michael Enright:        Quantum Dimension Inc., USA (menright@qdimension.com)

• Wenjian Luo:              Harbin Institute of Technology, Shenzhen, China (luowenjian@hit.edu.cn)

• Simon See:                        NVIDIA AI Technology Centre (ssee@nvidia.com)

• Tsungming (Nick) Tai: NVIDIA AI Technology Centre  (ntai@nvidia.com)

• Charles Cheung:            NVIDIA AI Technology Centre  (chcheung@nvidia.com)

• Lei Ma:                                   University of Alberta, Canada (ma.lei@acm.org)

Planned Activities in 2022/2023:

• Conference organization

  • C. Huang as Technical co-chair for IEEE ICDIS 2022

  • *C. Huang as Publicity co-chair for IEEE SSCI 2022

• Special sessions, workshops/symposiums, and competitions

  • *S. See and C. Huang, WCCI 2022 Industry Day Panel on ML application for Security and Privacy

• Tutorials, keynote and plenary talks, and webinars

  • Huiyu Zhou, invited to talk on CMI'22, FAIML'22, ECNLPIR'22, ICBIBE'22, AICS'22, ICIVIS'22, ICHVR'22, CSAE'22, ICIS'22, MLIS'22, and CFAIS'22.

  • Dipankar Dasgupta, available talks

    • Topic 1: Computational Intelligence in Cybersecurity (abstract)

    • Topic 2: Adversarial Machine Learning and Defense Strategies (abstract)

    • Topic 3: Adaptive Multi-Factor Authentication & Cyber Identity (abstract)

    • Topic 4: Advances in Immunological Computation (abstract)

    • Topic 5: AI vs AI: Viewpoints (abstract)

• Journal special issues

  • Zhou Tao, Chen Li, Lin Gu, Changming Sun, and Huiyu Zhou, Frontiers in Radiology, Research Topic "Computer-aided diagnosis based on medical image: trends and future research"

  • * W.Luo, Y. Jin and C. Huang, IEEE Transaction on AI Special Issue on Security & Privacy in ML

  • C. Huang, Y, Ong, and C. Fralick, Springer Complex and Intelligent Systems Special Issue on Secure Learning

• Other events aiming to promote the research, application and education relevant to Neural Networks

Completed Activities in 2022:

• Conference organization

  • Dipankar Dasgupta, Computational Intelligence in Cyber Security (CICS) at IEEE Symposium Series on Computational Intelligence (SSCI), Singapore, December 4-7, 2022.

• Special sessions, workshops/symposiums, and competitions

• Tutorials, keynote and plenary talks, and webinars

  • Huiyu Zhou, invited to talk on ICAIBD'22, ICIPMC'22, ICACDS'22, Huazhong University of Science and Technology, NUAA, Guangxi Minzu University, and Dalian University of Technology.

  • Dipankar Dasgupta, tutorial on “Machine Learning Applications, Adversarial Attacks and Mitigation Strategies” on December 5th  at IEEE Symposium Series on Computational Intelligence (SSCI), December 4-7, 2022.

• Journal special issues

• Other events aiming to promote the research, application and education relevant to Neural Networks

  • Singh, Amit Kumar, Huiyu Zhou, and Stefano Berretti. "Guest Editorial: Medical Data Security Solution for Healthcare Industries." IEEE Transactions on Industrial Informatics 18, no. 8 (2022): 5558-5560.

  • Dasgupta, Dipankar, and Kishor Datta Gupta. "Dual-filtering (DF) schemes for learning systems to prevent adversarial attacks." Complex & Intelligent Systems (2022): 1-22.

  • Dipankar Dasgupta and Sen, Sajib. An Empirical Study of Algorithmic Bias. A book Chapter in the Handbook on Computer Learning and Intelligence (Vol. II), pages 895-922, World Scientific Publisher, (2022).

  • Arunava Roy and Dipankar Dasgupta. A Robust Framework for Adaptive Selection of Filter Ensembles to Detect Adversarial Inputs. In Proceedings of  5th International Workshop on Dependable and Secure Machine Learning (DSML). Co-located with the 52nd IEEE/IFIP International Conference on Dependable Systems and Networks (DSN 2022),

  • Dasgupta, Dipankar, Zahid Akhtar, and Sajib Sen. "Machine learning in cybersecurity: a comprehensive survey." The Journal of Defense Modeling and Simulation 19, no. 1 (2022): 57-106.

  • Das, Lokesh Chandra, Dipankar Dasgupta, and Myounggyu Won. "LSTM-Based Adaptive Vehicle Position Control for Dynamic Wireless Charging." arXiv preprint arXiv:2205.10491(2022). (submitted to NeurIPS 2022)

  • Kishor Datta Gupta, Dipankar Dasgupta. Adversarial Attacks and Defenses for Deployed AI model. IT Professional Magazine (in press).

Completed Activities in 2020:

• The workshop of Secure Learning in IJCNN was held Tuesday, July 21st 2pm to 6pm (UK time).

• Propose and Organise the IJCNN Workshop on Secure Learning.