IEEE Conference on Secure and Trustworthy Machine Learning
February 8-10, 2023
Location to be revealed!
Sponsored by the IEEE Computer Society Technical Committee of Security and Privacy
Call for Papers
We solicit research papers, systematization of knowledge papers, and position papers.
Areas of Interest include (but are not limited to):
- Trustworthy data curation
- Novel attacks on ML systems
- Methods for defending against attacks on ML systems
- Forensic analysis of ML systems
- Verifying properties of ML systems
- Securely and safely integrating ML into systems
- Privacy (e.g., confidentiality, inference privacy, machine unlearning)
- The website for submissions is https://openreview.net/group?id=IEEE.org/SaTML/2023/Conference
- Submissions must use the two-column IEEE Proceedings style: https://www.ieee.org/conferences/publishing/templates.html
Research Papers, up to 12 pages of body text, with unlimited additional space for references and well-marked appendices. These must be well-argued and worthy of publication and citation, on the topics above. Research papers must present new work, evidence, or ideas.
Systematization of Knowledge papers, up to 12 pages of body text, should provide an integration and clarification of ideas on an established, major research area, support or challenge long-held beliefs in such an area with compelling evidence, or present a convincing, comprehensive new taxonomy of some aspect of secure and trustworthy machine learning.
Position papers with novel visions, with a minimum of 5 pages of body text, will also be considered. Reviewers will be asked to evaluate vision as bringing opinions and views that pertain to issues of broad interest to the computing community, typically, but not exclusively, of a nontechnical nature. Controversial issues will not be avoided but be dealt with fairly. Authors are welcome to submit carefully reasoned “Viewpoints” in which positions are substantiated by facts or principled arguments. Vision may relate to the wide and abundant spectrum of the computing field of trustworthy machine learning—its open challenges, technical visions and perspectives, educational aspects, societal impact, significant applications and research results of high significance and broad interest. Position papers should set the background and provide introductory references, define fundamental concepts, compare alternate approaches, and explain the significance or application of a particular technology or result by means of well-reasoned text and pertinent graphical material. The use of sidebars to illustrate significant points is encouraged.
At least one author of accepted papers will present their work at the conference and their papers will appear in the conference’s formal IEEE proceedings. In the event of difficulty in obtaining visas for travel and other exceptional circumstances, exceptions may be made and will be discussed on a case-by-case basis.
While a paper is under submission to this conference, authors may choose to give talks about their work, post a preprint of the paper online, and disclose security vulnerabilities to vendors.
- Abstracts due for Paper submissions: Monday August 22, 2022 (11:59 PM AoE, UTC-12)
- Paper submission: Thursday September 1, 2022 (11:59 PM AoE, UTC-12)
notification: Tuesday, November 15, 2022
- Camera-ready versions of Papers and Abstracts: Monday December 15, 2022
- Conference: Wednesday February 8 to Friday February 10, 2023
To improve the fairness of the reviewing process, SaTML will follow a double-blind reviewing process. Submitted papers must (a) omit any reference to the authors’ names or the names of their institutions, and (b) reference the authors’ own related work in the third person (e.g., not “We build on our previous work …” but rather “We build on the work of …”). Nothing should be done in the name of anonymity that weakens the submission or makes the job of reviewing the paper more difficult (e.g., important background references should not be omitted or anonymized). Please see the double-blind FAQ for the answers to many common concerns about SaTML’s double-blind reviewing process. When in doubt, contact the program chairs. We are devoted to seeking broad representation in the program, and may take this into account when reviewing multiple submissions from the same author.
Reviews from Prior Submissions
For papers that were previously submitted to, and rejected from, another conference, authors are required to submit a separate document containing the (anonymized, but otherwise unedited) prior reviews along with a description of how those reviews were addressed in the current version of the paper. Authors are only required to include reviews from the last time the paper was submitted. Authors who try to circumvent this rule (e.g., by changing the title of the paper without significantly changing the contents) may have their papers rejected without further consideration, at the discretion of the PC chairs.
Submissions must use the two-column IEEE Proceedings style: https://www.ieee.org/conferences/publishing/templates.html
Failure to adhere to these rules is grounds for rejection.
For each submission, one of the following decisions will be made:
- Accept: Papers in this category will be accepted for publication in the proceedings and presentation at the conference, possibly after making minor changes with the oversight of a shepherd (Minor Revision). Within one month of acceptance, all accepted papers must submit a camera-ready copy incorporating reviewer feedback. The papers will immediately be published, open access, in the Computer Society’s Digital Library, and they may be cited as “To appear in the IEEE Conference on Secure and Trustworthy Machine Learning, February 2023”.
- Major Revision: A limited number of papers will be invited to submit a major revision; such papers will receive a detailed summary of expectations for revision, in addition to standard reviewer comments. Authors will have a limited time window to submit revision after the notification is sent. The authors should clearly explain in a well-marked appendix how the revisions address the comments of the reviewers. The revised paper will then be re-evaluated, and either accepted or rejected. We will assign the same set of reviewers. Authors can choose to withdraw their paper and not submit a revision.
- Reject: Papers in this category are declined for inclusion in the conference.
We will have a rebuttal period during which authors have the opportunity to exchange messages with the reviewers, respond to questions asked, and address reviewer comments in the paper. To this end, we will use an anonymous communication feature to enable communication between authors and reviewers. The authors should mainly focus on factual errors in the reviews and concrete questions posed by the reviewers. New research results can also be discussed if they help to clarify open questions. More instructions will be sent out to the authors at the beginning of the rebuttal period.
Best Paper Award
Outstanding paper(s) will be selected by the Program Committee, with input from the Steering Committee, for the best paper award. The award will be announced at the conference. Best paper awards are intended to highlight papers which significantly challenge the state of the art in research areas relevant to SaTML.
If you have any questions, please email us at firstname.lastname@example.org