The 3rd New Frontiers

in Adversarial Machine Learning

(AdvML Frontiers @NeurIPS2024)

Dec. 14, 2024

East Ballroom C

Vancouver Convention Center

Vancouver, CA

About AdvML-Frontiers'24

Adversarial machine learning (AdvML), a discipline that delves into the interaction of machine learning (ML) with ‘adversarial’ elements, has embarked on a new era propelled by the ever-expanding capabilities of artificial intelligence (AI). This momentum has been fueled by recent technological breakthroughs in large multimodal models (LMMs), particularly those designed for vision and language applications. The 3rd AdvML-Frontiers workshop at NeurIPS’24 continues the success of its predecessors, AdvML-Frontiers’22-23, by delving into the dynamic intersection of AdvML and LMMs.

The rapid evolution of LMMs presents both new challenges and opportunities for AdvML, which can be distilled into two primary categories: AdvML for LMMs and LMMs for AdvML. This year, in addition to continuing to advance AdvML across the full theory-algorithm-application stack, the workshop is dedicated to addressing the intricate issues that emerge from these converging fields, with a focus on adversarial threats, cross-modal vulnerabilities, defensive strategies, multimodal human/AI feedback, and the overarching implications for security, privacy, and ethics. Join us at AdvML-Frontiers'24 for a comprehensive exploration of adversarial learning at the intersection with cutting-edge multimodal technologies, setting the stage for future advancements in adversarial machine learning. The workshop also hosts the 2024 AdvML Rising Star Award.

AdvML Rising Star Award Announcement

AdvML Rising Star Award was established in 2021 aiming at honoring early-career researchers (senior Ph.D. students and postdoc fellows), who have made significant contributions and research advances in adversarial machine learning. In 2024, the AdvML Rising Star Award will be hosted by AdvML-Frontiers'24 and two researchers are selected and awarded. The awardees will receive certificates and give an oral presentation of their work at the AdvML Frontiers 2024 workshop to showcase their research, share insights, and connect with other researchers in the field. Past Rising Star Awardees can be found at here.



Best Paper Awards

One or two best paper awards will be bestowed to the authors of the most exceptional paper. The award will carry a cash prize with a certificate. And the awardees will give an oral presentation of their research in the workshop.

Past Best Paper Awardees: AdvML-Frontiers'22 and AdvML-Frontiers'23

Keynote Speakers

Eleni Triantafillou

Eleni Triantafillou

Goolge Brain, UK

Franziska Boenisch

Franziska Boenisch

CISPA Helmholtz Center for Information Security, Germany

Hoda Heidari

Hoda Heidari

CMU, US

Alina Oprea

Alina Oprea

Northeastern, US

Schedule

To be determined ...



AdvML Rising Star Award

Application Instructions

Eligibility and Requirements: Senior PhD students enrolled in a PhD program before December 2021 or researchers holding postdoctoral positions who obtained PhD degree after April 2022.

Applicants are required to submit the following materials:
  • CV (including a list of publications)
  • Research statement (up to 2 pages, single column, excluding reference), including your research accomplishments and future research directions
  • A 5-minute video recording for your research summary
  • Two letters of recommendation uploaded to this form by the referees before September 9th, 2024 (AoE)
The awardee must attend the NeurIPS AdvML-Frontiers workshop and give a presentation in person. Submit the other required materials to this form by September 2nd, 2024 (AoE)


Submission deadline

Application material Sep 2 '24 AoE 00:00:00
Reference letters Sep 9 '24 AoE 00:00:00


Call For Papers

Submission Instructions

Submission Tracks

We welcome paper submissions from all the following tracks.

Track 1: Regular paper submission. This track accepts papers up to 6 pages with unlimited references or supplementary materials.

Track 2: Blue Sky Ideas/Position paper submission. This track invites submissions up to 6 pages, focusing on the “future” or “current” directions in AdvML. We welcome papers on visionary ideas, long-term challenges, current debates, and overlooked questions. This track aims to serve as an incubator for innovative and provocative research, providing a platform for the exchange of forward-thinking ideas without the constraints of result-oriented standards.

Track 3: Show-and-Tell Demos submission. This track allows papers up to 6 pages to demonstrate the practical innovations done by research and engineering groups. This track aims to create a unique opportunity to showcase the recent developments in the field through tangible demonstrations of systems, applications, services, and solutions.

Please ensure that all submissions conform to the AdvML-Frontiers'24 format template and please submit to OpenReview. Clearly specify the relevant track number in the title of your submission, for instance, by adding \usepackage[track1]{AdvML_Frontiers_2024} at the start of your main LaTeX document. Note that the track number is for review purposes only and will not be included in the final camera-ready version. The accepted papers are non-archival and non-inproceedings. Concurrent submissions are allowed, but it is the responsibility of the authors to verify compliance with other venues' policies. For NeurIPS, any neurips submissions can be submitted concurrently to workshops. Based on the PC’s recommendation, the accepted papers will be allocated either a spotlight talk or a poster presentation.  

Important Dates

Submission deadline Aug. 30 '24 AoE 00:00:00
Notification to authors Oct. 9 '24 AoE


Topics

The topics for AdvML-Frontiers'24 include, but are not limited to:

  • Adversarial threats on LMMs
  • Cross-modal adversarial vulnerabilities for LMMs
  • Defensive strategies and adversarial training techniques for LMMs
  • Ethical implications of AdvML in LMMs
  • Privacy and security in LMMs, (e.g., membership inference attack vs. machine unlearning, watermarking vs. model stealing)
  • LMM-aided AdvML (e.g., for attack and defense enhancements)
  • Offensive use of LMMs in security
  • Novel applications of AdvML for LMMs and LMMs for AdvML
  • Mathematical foundations of AdvML (e.g., geometries of learning, causality, information theory)
  • Adversarial ML metrics and their interconnections
  • New optimization methods for adversarial ML
  • Theoretical understanding of adversarial ML
  • Data foundations of adversarial ML (e.g., new datasets and new data-driven algorithms)
  • Scalable adversarial ML algorithms and implementations
  • Adversarial ML in the real world (e.g., physical attacks and lifelong defenses)
  • Provably robust machine learning methods and systems
  • New adversarial ML applications
  • Explainable, transparent, or interpretable ML systems via adversarial learning techniques
  • Fairness and bias reduction algorithms in ML
  • Adversarial ML for good (e.g., privacy protection, education, healthcare, and scientific discovery)


Official Twitter Account

AdvML-Frontiers 2024 Venue

venue

NeurIPS 2024 Workshop
Physical Conference

AdvML-Frontiers'24 will be held in person with possible online components co-located at the NeurIPS 2024 workshop and the conference will take place in the beautiful Vancouver Convention Center, Vancouver, CA.

Organizers

Sijia Liu

Sijia Liu

Michigan State University, USA

Pin-Yu Chen

Pin-Yu Chen

IBM Research, USA

Dongxiao Zhu

Dongxiao Zhu

Wayne State University, USA

Eric Wong

Eric Wong

University of Pennsylvania, USA

Yao Qin

Qin Yao

UC Santa Barbara, USA

Kathrin Grosse

Kathrin Grosse

EPFL, Switzerland

Sanmi Koyejo

Sanmi Koyejo

Stanford, USA



Workshop Activity Student Chairs

Contacts

Please contact advml_frontiers24@googlegroups.com for paper submission and logistic questions.



Program Committee Members

Mathias Humbert (University Lausanne)
Maura Pintor (University of Cagliari)
Maksym Andriuschenko (EPFL)
Yuguang Yao (Michigan State University)
Yiwei Chen (Michigan State University)
Yimeng Zhang (Michigan State University)
Changsheng Wang (Michigan State University)
Soumyadeep Pal (Michigan State University)
Parikshit Ram (IBM Research)
Ruisi Cai (UT Austin (NVIDIA))
Zhenyu Zhang (UT Austin)
Pingzhi Li (UNC)
Haomin Zhuang (Notre Dame)
Changchang Sun (IIT)
Ren Wang (IIT)
Jiabao Ji (UCSB)
Zichen Chen (UCSB)
Deng Pan (University of Notre Dame)
Yao Qiang (Wayne State University)
Rhongho Jang (Wayne State University)
Huaming Chen (The University of Sydney)
Kaiyi Ji (University at Buffalo)
Hossein Hajipour (CISPA)
Siddharth Joshi (UCLA)
Dang Nguyen (UCLA)
Jiayi Ni (UCLA)
Fateme Sheikholeslami (Amazon)
Francesco Croce (EPFL)
Chia-Yi Hsu (NYCU)
Yu-Lin Tsai (NYCU)
Zichong Li (UT Austin)
Zhiyuan He (CUHK)
Shashank Kotyan (Kyushu University)
Zhenhan Huang (RPI)
Wenhan Yang (UCLA)
Jiancheng Liu (Michigan State University)
Chongyu Fan (Michigan State University)
Yuhao Sun (USTC)
Jiaxiang Li (UMN)
Qiucheng Wu (UCSB)
Ioannis Tsaknakis (UMN)
David Pape (CISPA)
Jonathan Evertz (CISPA)
Joel Frank (Ruhr Universität Bochum)
Maximilian Baader (ETH Zurich)
Chirag Agarwal (UVA)
Naman Deep Singh (University of Tubingen)
Christian Schlarmann (University of Tubingen)
Zaitang Li (CUHK)
Chen Xiong (CUHK)
Erh-Chung Chen (NTHU)
Litian Liu (Qualcomm)
Mathilde Raynal (EPFL)
Lena Schoenherr (CISPA)
Yize Li (NEU)
Xin Li (Bosch AI)
Xinlu Zhang (UCSB)
Srishti Gupta (Università di Roma la Sapienza)
Kenan Tang (UCSB)
Prashant Khanduri (Wayne State University)
Ziqi Gao (HKUST)
Aochuan Chen (HKUST)
Junyuan Hong (UT Austin)
Emanuele Ledda (Università di Roma la Sapienza)
Guanhua Zhang (Max Planck Institute for Intelligent Systems)
Giovanni Appruzese (University Liechtenstein)

More to be confirmed ...