4^th ICDM MLC Workshop

December 9, 2024
Abu Dhabi, UAE

Machine Learning for Cybersecurity (MLC)

Keynote Speakers

Trustworthy and Privacy-Preserving Machine Learning Inference Services
Thang Hoang, Virginia Tech
Abstract: TBD Dr. Thang Hoang is an Assistant Professor in the Department of Computer Science at Virginia Tech and a CCI Researcher. Prior to joining Virginia Tech, Thang was a Postdoctoral Fellow at Carnegie Mellon University (CMU) hosted by Prof. Elaine Shi and a Research Associate at the University of South Florida (USF) hosted by Prof. Attila A. Yavuz. He received a PhD degree from USF in August 2020. Thang's research spans the domains of cybersecurity and applied cryptography, with interests in privacy, secure and verifiable computation, zero-knowledge proofs, fuzzy cryptography, and trustworthy machine learning..
Towards Robustness Analysis of AIGC Systems
Kailong Wang, Huazhong University of Science and Technology
Abstract: The rapid advancement of AI technologies in user-oriented software systems has introduced novel challenges in ensuring system robustness. In this talk, I will first introduce Drowzee, our innovative approach that combines logic programming and metamorphic testing to detect fact-conflicting hallucinations in LLMs. Drowzee constructs factual knowledge bases, represents facts as logical predicates, and applies reasoning rules to generate logically sound question-answer pairs for testing LLMs, using semantic-aware metamorphic oracles to identify potential hallucinations. Next, I will discuss our research on "glitch tokens", anomalous tokens produced by tokenizers that can compromise LLM response quality. We categorized glitch tokens, observed LLM symptoms when interacting with them, and developed GlitchHunter, an iterative clustering-based detection technique that outperformed three baselines on eight open-source LLMs, offering insights into mitigating tokenization-related errors. Dr. Kailong Wang is currently an associate professor (with tenure) in the School of CSE at Huazhong University of Science and Technology (HUST). He is broadly interested in AI+Security, Secure and Private Software Engineering. He has published in various top-tier conferences and journals such as OOPSLA, NDSS, MobiCom, TSE, TOSEM, FSE, ASE, ISSTA and WWW.

Call For Paper

In the past decades, cybersecurity threats have been among the most significant challenges for social development resulting in financial loss, violation of privacy, damages to infrastructures, etc. Organizations, governments, and cyber practitioners tend to leverage state-of-the-art Artificial Intelligence technologies to analyze, prevent, and protect their data and services against cyber threats and attacks. Due to the complexity and heterogeneity of security systems, cybersecurity researchers and practitioners have shown increasing interest in applying data mining methods to mitigate cyber risks in many security areas, such as malware detection and essential player identification in an underground forum. To protect the cyber world, we need more effective and efficient algorithms and tools capable of automatically and intelligently analyzing and classifying the massive amount of data in cybersecurity complex scenarios. This workshop will focus on empirical findings, methodological papers, and theoretical and conceptual insights related to data mining in the field of cybersecurity.

The workshop aims to bring together researchers from cybersecurity, data mining, and machine learning domains. We encourage a lively exchange of ideas and perceptions through the workshop, focused on cybersecurity and data mining. Topics of interest include, but are not limited to:

• Security and privacy of Data Mining
• Data mining and AI applications for cybersecurity
• Data mining approaches to enhance security and resiliency of cyber systems
• Human behavior models with application to cybersecurity
• Data mining for cybersecurity software verification and validation
• AI tools and techniques to enhance resilience in cybersecurity
• AI-enabled automation of cybersecurity tasks
• Data-driven cybersecurity Analytics
• Uncertainty-based decision making in cybersecurity
• Modeling and simulation of cyber systems and system components

• Adversarial machine learning
• Cryptography
• Large language models
• Interpretable deep learning
• Multi-view deep learning paradigms
• Real-time analytics and deep learning on stream data
• Deep Transfer learning
• Deep reinforcement learning
• Bayesian deep learning
• Graph convolutional networks and graph attention networks

• Malware evasion and detection
• Cyber threat detection and modeling
• Intrusion detection
• Internet of Things (IoT) analysis
• AI-enabled security information sharing and automation across multiple data sources
• Smart and large-scale vulnerability assessment
• Intelligent security systems with human-in-the-loop
• Vulnerability detection
• Anomaly detection
• Dark Web Analytics for CTI applications
• IP reputation analysis

Important Dates

• Workshop papers submission: September 10, September 22, 2024
• Notification of workshop papers acceptance to authors: October 7, 2024
• Camera-ready deadline and copyright form: October 11, 2024
• Workshops date: December 9, 2024

Paper Submission

Organizers

Steering Chairs

Ali Babar University of Adelaide	Battista Biggio University of Cagliari	Elisa Bertino Purdue University
Hsinchun Chen University of Arizona	Yang Liu Nanyang Technological University	Xinming (Simon) Ou University of South Florida

Program Chairs

Sin Gee Teo Institute for Infocomm Research	RuiTao Feng Singapore Management University	Reza Ebrahimi University of South Florida

Rouzbeh Behnia University of South Florida	Jason Pacheco University of Arizona	Yulei Sui University of New South Wales

Guangdong Bai University of Queensland

Local Chairs

Mohamed Ragab Technology Innovation Institute

Publicity Chairs

Yuekang Li University of New South Wales	Shangqing Liu Nanyang Technological University

Program Committee

• Guangdong Bai, University of Queensland
• Rouzbeh Behnia, University of South Florida
• Yidong Chai, Hefei University
• Sen Chen, Tianjin University
• M.A.P. Chamikara, CSIRO DATA61
• Luca Demetrio, University of Cagliari
• Ambra Demontis, University of Cagliari
• Habiba Farrukh, Perdue University
• Kaushik Dutta, University of South Florida
• Antonio Emanuele Cina', Ca' Foscari University of Venice
• Hossein Hamooni, Meta
• Thang Hoang, Virginia Tech
• Matthew Jagielski, Google Research
• Yun Lin, Shanghai Jiao Tong University
• Zahid Islam, Charles Sturt University
• Murat Kantarcioglu, University of Texas, Dallas
• Ryan Ko, University of Queensland
• Ruofan Liu, National University of Singapore
• Lei Ma, University of Alberta
• Guozhu Meng, Institute of Information Engineering of Chinese Academy of Sciences/University of Chinese Academy of Sciences
• Cen Zhang, Nanyang Technological University
• Maura Pintor, University of Cagliari
• Fabio Pierazzi, King's College London
• Alina Oprea, Northeastern University
• Muslum Ozgur Ozmen, Arizona State University
• Balaji Padmanabhan, University of South Florida
• Konrad Rieck, Technische Universität Berlin
• Arash Shaghaghi, University of New South Wales
• Angelo Sotgiu, University of Cagliari
• Yulei Sui, University of New South Wales
• Bhavani Thuraisingham, University of Texas, Dallas
• Faheem Ullah, University of Adelaide
• Yuekang Li, University of New South Wales
• Xiaofei Xie, Singapore Management University
• Xun Yi, Royal Melbourne Institute of Technology
• Hellen Zhang, University of Arizona
• Mehran Mozaffari Kermani, University of South Florida
• Attila A Yavuz, University of South Florida