The 4th ARTMAN workshop co-located with IEEE ACSAC 2026 (December 7 or 8, 2026 -- Los Angeles, CA, USA)
Overview
This workshop aims at bringing together academic researchers and industrial practitioners from different domains with diverse expertise (mainly security & privacy and artificial intelligence (AI)/machine learning (ML), but also from application domains) to collectively explore and discuss the topics about resilient and trustworthy machine learning-powered applications and systems, share their views, experiences, and lessons learned, and provide their insights and perspectives, so as to converge on a systematic approach to securing them.
Topics of Interest
This workshop will be focused on the resilience and trustworthiness of AI/ML-driven systems. Resilience refers to the ability of an AI/ML system to maintain required capability and expected performance in the face of adversity, covering both dependability (accidental failures) and security (intentional attacks) issues. Trustworthiness refers to the attribute that an AI/ML system provides confidence to users of their capabilities and reliability in performing given tasks.
Topics of interest include (but are not limited to):
- Trust in intelligent systems and applications mainly explores the trust issues arising from the interactions between human users and AI systems (e.g., Man-Machine Symbiosis, Human-Machine Teaming, AI agents) with a particular focus on interpretable, explainable, accountable, transparent, and fair intelligent systems, and applications in intelligent systems
- AI/ML robustness and security evaluation: testing, simulation, verification, validation, and certification of the robustness and security of AI/ML pipelines (not only algorithms and models) in intelligent systems, including but not limited to data-centric analytics, model-driven methods, and hybrid methods
- Adversarial machine learning, including adversarial examples of input data and adversarial learning algorithms developed for intelligent systems
- Threat modeling and risk assessment of intelligent systems and of applications in intelligent systems, including, but not limited to, anomaly detection, failure prediction, root cause analysis, incident diagnosis
- Data-centric attacks and defenses of intelligent systems and applications, such as model evasion via targeted perturbations in testing samples, data poisoning in training examples, as well as backdoor attacks
- Resilience by reaction: leveraging AI/ML algorithms, especially knowledge-informed models, to improve resilience and trust of intelligent systems
- Machine unlearning: measures to protect users' privacy against ML-based threats
- Sustainable AI: usable and robust small AI models; privacy-aware distillation or compression techniques; robust and trustworthy Federated Learning, trustworthy AI agents and embodied AI
Proceedings
The proceedings of the 4th ARTMAN workshop will be published in a supplementary volume along IEEE ACSAC 2026 proceedings. More information will be available later.
Submission Guidelines
Papers can be submitted in two categories: regular and short ones.
- Regular submissions should be 10 pages excluding references and appendices, using double-column IEEE template available here with \documentclass[conference,compsoc]{IEEEtran}. 5 additional pages can be used for references and well-referenced appendices. Note that the reviewers are not expected to read these appendices.
- Short submissions are limited to 4 pages excluding references and appendices.
- All submissions must be anonymous, i.e., author names and affiliations should not be included. Authors can cite their work but must do so in the third person.
- Accepted workshop papers will be published by IEEE Computer Society Conference Publishing Services (CPS), see below.
Papers that are not properly anonymised or do not follow the IEEE Conference Template will be desk-rejected.
AI Policy on Usage of LLMs
Authors may use large language models (LLMs) and other generative AI tools when preparing their submissions. However, all use must be disclosed, and authors bear full responsibility for the correctness, originality, and integrity of their work. Undisclosed or irresponsible use of LLMs is grounds for desk rejection. If LLMs are used, authors must include a separate, clearly marked section titled “LLM Usage Statement” at the end of the paper. This section does not count towards the page limit. More information can be found
ACSAC webpage.
Submission Link
HotCRP
Important Dates
- Submission Deadline: September 1-5, 2026 (TBC)
- Acceptance Notification: October 5-10, 2026 (TBC)
- Camera-Ready Deadline: October 26-31 (TBC)
- Workshop Day: December 7 or 8, 2026
Visa Request for Workshop Participants
Authors requiring a visa to enter the USA need to start the process as soon as possible. For information on requesting a Visa letter, please click here. Registration payment is required prior to the issuance of a visa letter. Attendees requiring additional time to receive their visa may pre-register by wire, transferring an advance payment in conjunction with submitting a Visa Letter Request.
Organizing Committee
Program Chairs
- Gregory Blanc (Telecom SudParis, Institut Polytechnique de Paris, France)
- Takeshi Takahashi (National Institute of Information and Communications Technology, Japan)
- Zonghua Zhang (IMT Nord Europe)
TPC Members
- Muhamad Erza Aminanto (Monash University, Indonesia)
- Andrea Ceccarelli (University of Florence, Italy)
- Frédéric Majorczyk (DGA, France)
- Antonio Muñoz (University of Malaga, Spain)
- Gustavo Sánchez Collado (Nemko Digital, Germany)
- Shreya Sharma (Meta, USA)
- Pierre-Martin Tardif (Université de Sherbrooke, Canada)
- Fredrik Warg (RISE Research Institutes of Sweden)
This workshop is co-located with the IEEE ACSAC 2026 conference and is partially supported by the GRIFIN project (ANR-20-CE39-0011).