MLHat @ KDD 2021

MLHat: The 2nd International Workshop on Deployable Machine Learning for Security Defense

15 August 2021 — Virtual Space
co-located with 26TH ACM SIGKDD Conference on Knowledge Discovery and Data Mining


The 2nd MLHat workshop will be co-located with KDD 2021!

Paper submission deadline is extended to June 4, 2021


Farinaz Koushanfar, UC San Diego

Farinaz Koushanfar is a professor and Henry Booker Faculty Scholar in the Electrical and Computer Engineering (ECE) department at University of California San Diego (UCSD), where she is the founding co-director of the UCSD Center for Machine Intelligence, Computing & Security (MICS). Prof. Koushanfar received her Ph.D. in Electrical Engineering and Computer Science as well as her M.A. in Statistics from UC Berkeley. Her research addresses several aspects of efficient computing and embedded systems, with a focus on system and device security, safe AI, privacy preserving computing, as well as real-time/energy-efficient AI under resource constraints, design automation and reconfigurable computing. Professor Koushanfar has received a number of awards and honors for her research, mentorship, teaching, and outreach activities including the Presidential Early Career Award for Scientists and Engineers (PECASE) from President Obama, the ACM SIGDA Outstanding New Faculty Award, Cisco IoT Security Grand Challenge Award, Qualcomm Innovation Award(s), MIT Technology Review TR-35, Young Faculty/CAREER Awards from NSF, DARPA, ONR and ARO, as well as a number of Best Paper Awards. Dr. Koushanfar is a fellow of the IEEE, and a fellow of the Kavli Foundation Frontiers of the National Academy of Sciences.

Call for Papers

Important Dates

  • Paper submission deadline: May 20, 2021 June 4, 2021
  • Acceptance notification: June 20, 2021 June 25, 2021
  • Talk video due: TBD
  • Camera ready due: TBD
  • Workshop: August 15, 2021


In recent years, we have seen machine learning algorithms, particularly deep learning algorithms, revolutionizing many domains such as computer vision, speech, and natural language processing. In contrast, the impact of these new advances in machine learning is still fairly limited in the domain of security defense. While there is research progress in applying  machine learning for threat forensics, malware analysis, intrusion detection, and vulnerability discovery, there are still grand challenges to be addressed before a machine learning system can be deployed and operated in practice as a critical component of cyber defense. Major challenges include but not limited to the scale of the problem (billions of known attacks), adaptability (hundreds of millions of new attacks every year),  inference speed and efficiency (compute resource is constrained), adversarial attacks (highly motivated evasion and poisoning attacks), the urging demand for explainability (for threat investigation), and the need for integrating human (e.g., SOC analysts) in the loop. 

This workshop aims to bring together academic researchers and industry practitioners to discuss the open challenges, potential solutions, and best practices to deploy machine learning at scale for security defense. The goal is to define new machine learning paradigms under various security application contexts and identifying exciting new future research directions. At the same time, the workshop will also have a strong industry presence to provide insights into the challenges in deploying and maintaining machine learning models, and the much needed discussion on the capabilities that the state-of-the-arts failed to provide.

Topics of Interest

Topics of interest include (but not limited to):

  • Malware analysis, detection, classification, and attribution
  • Vulnerability discovery using machine learning
  • ML applications for cloud infrastructure and IoT security
  • Network attack detection, classification, and analysis
  • Spam, phishing, online scam detection
  • Malicious behaviors in online social networks
  • Sequence analysis for system/network events
  • Anomaly detection
  • Model verdict explainability in security applications
  • Privacy preserving security data collection and sharing
  • Robustness of machine learning models against adversarial attacks
  • Concept drift detection and explanation
  • Interactive machine learning for security
  • Few-shot learning for security applications
  • Resource constrained machine learning
  • Deep and shallow learning applications

Submission Guidelines

We welcome different types of papers, including:  

  • Novel research papers
  • Work-in-progress papers
  • Visionary and position papers
  • Papers that describe real-world security data sets

We ask the authors to clearly specify the paper type in the abstract, to help reviewers assess the contributions. Submissions must be in PDF and formatted according to the templates linked below. The main content of the paper should be 20-25 single-column pages of content with unlimited number of pages for appendices and references (equivalent to 7-8 pages of standard double-column ACM Sigconf Proceedings Style). Each submission will be single-blind reviewed by at least 3 PC members.

Accepted papers will be archived as full papers in Springer Communications in Computer and Information Science (CCIS) and will be presented orally during the workshop. At least one author of each accepted paper must attend the workshop to present the work in order for the paper to be archived.

Paper template: LaTex, Word, Overleaf

Submission Site


Workshop Chairs

Gang Wang, UIUC, USA
Arridhana Ciptadi, TruEra, USA
Ali Ahmadzadeh, Blue Hexagon, USA

Program Committee

Binghui Wang, Duke University
Zhou Li, UC Irvine
Fabio Pierazzi, King’s College London
Gianluca Stringhini, Boston University
Ting Wang, Penn State University
Wenbo Guo, Penn State University
Alborz Rezazadeh, LG AI Research Lab
Sadia Afroz, Avast
Siddharth Bhatia, National University of Singapore