Workshop on Recent Advances in Resilient and Trustworthy ML Systems in Autonomous Networks

Overview

This workshop aims at bringing together academic researchers and industrial practitioners, from different domains with diverse expertise (mainly networking, security, machine learning), to collectively explore and discuss the topics about resilient and trustworthy autonomous networks, share their views, experiences, and lessons learned.

Topics of Interest

Topics of interest include (but are not limited to):

• Threat modeling and risk assessment of ML systems and applications in autonomous networks, including, but not limited to, anomaly detection, failure prediction, root cause analysis, incident diagnosis
• Data-centric attacks and defenses of ML systems and applications in autonomous networks, such as model evasion via targeted perturbations in testing samples, data poisoning in training examples
• Adversarial machine learning, including adversarial examples of network data (e.g., time series, network traffic, logs, graph data) and adversarial learning algorithms developed for autonomous networks
• ML robustness: testing, simulation, verification, validation, and certification of robustness of ML pipelines (not only ML algorithms and models) in autonomous networks, including but not limited to data-centric analytics, model-driven methods, and hybrid methods
• ML system safety, which mainly addresses the topics related to ML system development and deployment environments, including hardware, ML platform and framework, software
• Trust in ML systems and applications, which aims to explore the trust issues arising from the interactions between human users and machine learning systems, with particular focus on interpretable, explainable, accountable, transparent, reliable, and fair ML systems and applications in autonomous networks
• Resilience by reaction: Leveraging AI/ML algorithms, especially knowledge-informed models, to improve resilience and trust of autonomous networks

Programme

Time	Duration	Speakers	Title
10:00-10:15	15 mns	Gregory BLANC, Takeshi TAKAHASHI, Zonghua ZHANG	ARTMAN '23 Workshop opening
10:15-11:15	60 mns	Sandra SCOTT-HAYWARD	Keynote #1: Secure, intelligent, programmable space-air-ground integrated networks
11:15-11:30	15 mns	Break
11:30-12:20	50 mns	Resilience Session
11:30-12:00	30 mns	Bahrul Ilmi NASUTION, Yudhistira NUGRAHA, Irfan Dwiki BHASWARA, Muhamad Erza AMINANTO	How Resilient is Privacy-preserving Machine Learning Towards Data-Driven Policy? Jakarta COVID-19 Patient Study Case
12:00-12:20	20 mns	Soohyun JUNG, Keisuke FURUMOTO, Takeshi TAKAHASHI, Yoshiaki SHIRAISHI	Model Selection for Continuous Operation of Automated Vulnerability Assessment System
12:20-14:00	100 mns	Lunch
14:00-15:00	60 mns	Konrad RIECK	Keynote #2: When Papers Choose Their Reviewers: Adversarial Machine Learning in Peer Review
15:00-15:15	15 mns	Break
15:15-16:15	60 mns	Robustness Session
15:15-15:45	30 mns	Romain ILBERT, Thai V. HOANG, Zonghua ZHANG, Themis PALPANAS	Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecasting
15:45-16:15	30 mns	Muhammad Akbar HUSNOO, Adnan ANWAR, Robin Ram Mohan DOSS, Nasser HOSSEINZADEH	Towards Robust Misbehavior Detection in Power Control Systems: A Gradient Quantization Approach
16:15-16:30	15 mns	Break
16:30-16:50	20 mns	Explainability Session
16:30-16:50	20 mns	Harry Chandra TANUWIDJAJA, Takeshi TAKAHASHI, Tsungnan LIN, Boyi LEE, Tao BAN	Hybrid Explainable Intrusion Detection System: Global vs. Local Approach
16:50-17:05	15 mns	Gregory BLANC, Takeshi TAKAHASHI, Zonghua ZHANG	Closing remarks

Submission Guidelines

Papers can be submitted in two categories: regular and short ones.

• Regular workshop paper submissions must be at most 10 pages in double-column ACM format, excluding the bibliography and well-marked appendices, and at most 12 pages overall.
• Short papers are limited to 6 pages in total (4 pages without bibliography and appendices).
• Papers should be prepared in ACM format using latex. Please follow the main CCS formatting instructions to prepare the submissions. The sigconf template is available here.
• All submissions must be in English and properly anonymized.
• All the accepted papers (both regular and short versions) will be included in the proceedings and published by the ACM Digital Library and/or ACM Press.

Please note that TPC members are not required to read the appendices, so the paper should be intelligible without them.

Submission Link

HotCRP

Important Dates

• 21 July, 2023: Submission Deadline
• 28 August, 2023: Acceptance Notification
• 10 September, 2023: Camera-Ready Paper Submission Deadline
• 30 November, 2023: Workshop

Organizing Committee

Program Chairs

• Gregory Blanc (Télécom SudParis, France)
• Takeshi Takahashi (National Institute of Information and Communications Technology, Japan)
• Zonghua Zhang (Huawei Paris Research Center, France)

TPC Members

• Muhamad Erza Aminanto (Monash University, Indonesia)
• Agathe Blaise (Thales, France)
• Andrea Ceccarelli (University of Florence, Italy)
• Sajjad Dadkhah (University of New Brunswick, Canada)
• Doudou Fall (Ecole Supérieure Polytechnique, Cheikh Anta Diop University, Senegal)
• Pierre-François Gimenez (CentraleSupélec, France)
• Yufei Han (Inria, France)
• Houda Jmila (Télécom SudParis, France)
• Hsiao-Ying Lin (Huawei Technologies, France)
• Frédéric Majorczyk (DGA, France)
• Johan Mazel (ANSSI, France)
• Ikuya Morikawa (Fujitsu, Japan)
• Antonio Muñoz (University of Malaga, Spain)
• Paul Pang (Federation University, Australia)
• Toshiki Shibahara (NTT, Japan)
• Pierre-Martin Tardif (Université de Sherbrooke, Canada)
• Akira Yamada (Kobe University, Japan)
• Shui Yu (University of Technology Sydney, Australia)
• Xiangliang Zhang (University of Notre Dame, USA)

Sponsor

This workshop is co-located with the ACM CCS '23 conference and is partially supported by the GRIFIN project (ANR-20-CE39-0011).