iiinova — where your digital self keeps evolving

Conference on Secure and Trustworthy Machine Learning @satml.org · 09/09/2026

The submission server for #SaTML2027 is now open! There are also some changes to the Call for Papers, diffs are indicated on the website. Dates: Mandatory abstract deadline: Sep 22 Paper deadline: Sep 29 satml.org

196

Conference on Secure and Trustworthy Machine Learning @satml.org · 25/08/2026

The Call for Papers for #SaTML2027 is released! Deadlines: Abstract - Sep 22 Paper - Sep 29 Decisions - Dec 16 New this year: abstract deadline, initial review & ACs, mandatory artifact submission, planning for growth in submissions, etc. Full details: satml.org/call-for-pap...

122

Conference on Secure and Trustworthy Machine Learning @satml.org · 21/08/2026

Reminder: #SaTML2027 has a Call for Competitions and Workshops! Both are due one week from today (August 28). Please submit your proposals and join us in beautiful Reykjavik! satml.org/call-for-com... satml.org/call-for-wor...

052

Conference on Secure and Trustworthy Machine Learning @satml.org · 23/07/2026

On top of our Call for Papers, #SaTML2027 has a Call for Competitions and a Call for Workshops (first time ever!!). Dates (easy to remember, same for both) Deadline: August 28, 2026 Notifications: September 18, 2026 Topics can be anything in trustworthy and secure ML!

112

Conference on Secure and Trustworthy Machine Learning @satml.org · 30/06/2026

Buried in yesterday's announcement of the location (Reykjavik, Iceland), we have also released Calls for: - Papers (research, position, and SoK), deadline September 29, 2026 - Competitions - Workshops, for the first time ever at SaTML! Check out the wbsite for more info on all! satml.org

021

Conference on Secure and Trustworthy Machine Learning @satml.org · 29/06/2026

We're pleased to announce that #SaTML2027 will be in Reykjavik, Iceland! Thanks to General Chair Giovanni Apruzzese for making the arrangements. The conference will be in early May 2027. Get your submissions ready: the deadline will be September 29, 2026. Details on the new website: satml.org

074

Conference on Secure and Trustworthy Machine Learning @satml.org · 07/04/2026

The program chairs for #SaTML2027 will be Fabio Pierazzi (@fbpierazzi.bsky.social) and Florian Tramèr! We're in for a great conference under their leadership.

042

Conference on Secure and Trustworthy Machine Learning @satml.org · 06/04/2026

SaTML is looking for a host for #SaTML2027! If you're interested in bringing SaTML to a city near you, please fill out this form by April 15! 🏘️🏙️🏡🌆 docs.google.com/forms/d/e/1F...

075

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🔍 How private was that release? @a-h-koskela.bsky.social presents a method for auditing DP guarantees using density estimation. #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🧮 Getting the math right. @matt19234.bsky.social walks through common traps in privacy accounting and how to avoid them. #SaTML25

031

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🧠 Marginals leak. Steven Golob shows how synthetic data built on marginals can still compromise privacy. Paper: arxiv.org/abs/2410.05506 #SaTML25

200

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

📃🔐 Privacy and fairness? Khang Tran introduces FairDP, enabling fairness certification alongside differential privacy. Paper: arxiv.org/abs/2305.16474 #SaTML25

100

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🖼️📡 Hide and seek. Luke Bauer presents a method for covert messaging with provable security via image diffusion. Paper: arxiv.org/abs/2503.10063 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

💣 Still work to do. Yigitcan Kaya makes the case that ML-based behavioral malware detection is fragile and far from solved. Paper: arxiv.org/abs/2405.06124 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

💻 What can you learn privately when compute is tight? Zachary Charles tackles user-level privacy under realistic constraints. #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

📊 Not all public datasets are equal. Xin Gu proposes a new metric—gradient subspace distance—to guide private learning choices. Paper: arxiv.org/abs/2303.01256 #SaTML25

031

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

📚🔒 Choose wisely. Kristian Schwethelm presents a method to balance data utility and privacy in active learning. Paper: arxiv.org/abs/2410.00542 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

⚖️ Privacy isn’t always fair. Kai Yao breaks down the mechanisms that can introduce unfairness into private learning. Paper: arxiv.org/abs/2501.14414 #SaTML25

010

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🌲💀 Even decision trees aren’t safe. Lorenzo Cazzaro shows how to poison tree-based models. Paper: arxiv.org/abs/2410.00862 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🚗🔦 How robust are LiDAR detectors?Alexandra Arzberger presents Hi-ALPS, benchmarking six systems used in autonomous vehicles. Paper: arxiv.org/abs/2503.17168 #SaTML25

100

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🎯 Robustness meets domain adaptation. Natalia Ponomareva introduces DART, a principled method for adapting without labels—and withstanding attacks. #SaTML25

100

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🔍 A fairness reality check. Claire Zhang surveys the landscape of fair clustering—what works, what doesn’t, and what’s next. #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🎯 Adversarial incentives meet fairness. Emily Diana presents a minimax approach to fairness when users can game the system. #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🌀 Trying to be fair… and failing? Natasa Krco argues that efforts to reduce bias can themselves be arbitrary—or even unfair. #SaTML25

010

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

🌍 No central authority, no problem?Sayan Biswas explores fairness challenges and solutions in decentralized learning systems. Paper: arxiv.org/abs/2410.02541 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 11/04/2025

☀️ Kicking off the final day of #SaTML25 with a big question: Should you trust artificial intelligence? Matt Turek takes the stage for this morning’s keynote on the path toward trustworthy AI.

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

🌈 Can machines see color like we do? Ming-Chang Chiu presents ColorSense, exploring color perception in machine vision. Paper: arxiv.org/abs/2212.08650 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

🪵🧵 Texture vs. shape. Blaine Hoak dives into real-world evidence of texture bias in vision models. Paper: arxiv.org/abs/2412.10597 #SaTML25

011

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

📎 Perception with CLIP. Christian Schlarmann shows how robustness in CLIP models improves perceptual metrics. Paper: arxiv.org/abs/2502.11725 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

🎯 Not all queries are equal. Lorenz Wolf presents a mechanism for private selection under varying sensitivity levels. Paper: arxiv.org/abs/2501.05309 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

🔗 When noise talks. Haewon Jeong explores how correlated privacy can improve distributed mean estimation. Paper: arxiv.org/abs/2407.03289 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

📊 Stream, count, forget (privately). Rasmus Pagh presents a binning-based method for continual private counting. Paper: arxiv.org/abs/2412.07093 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

📱🛡️ Second competition: Robust Android Malware Detection. How robust is your malware detector—over time and under attack? Maura Pintor shares what the competition revealed. More info: ramd-competition.github.io #SaTML25

020

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

📄🔍 First competition: Inference Attacks Against Document VQA. Can you extract sensitive information from Document Visual Question Answering models? Andrey Barsky walks us through the results. More info: benchmarks.elsa-ai.eu?ch=2&com=int... #SaTML25

020

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

🔍 A reality check. Amrita Chowdhury revisits how reliable membership inference attacks really are when used to evaluate unlearning. #SaTML25

010

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

📉 Are we measuring the right things? Pratiksha Thaker argues current benchmarks for unlearning in language models fall short. #SaTML25

110

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

🚨 Unlearning ≠ privacy. Jamie Hayes warns that inexact unlearning can give a false sense of security without rigorous evaluation. Paper: arxiv.org/abs/2403.01218 #SaTML25

100

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

🔐 Forget it, securely. @eisenhofer.bsky.social l presents a framework for verifiable and provably secure machine unlearning. Paper: arxiv.org/abs/2210.09126 #SaTML25

141

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

📌 More than meets the patch. Mauricio Byrd Victorica presents SpaNN, which detects multiple adversarial patches using saliency thresholding. #SaTML25

010

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

🕵️‍♀️ Forensics for ML. Ilia Shumailov introduces SEA, a system that tracks black-box attacks using query sequences. Paper: arxiv.org/abs/2308.11845 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

🧬 Tweaking the manifold. Banibrata Ghosh shows how targeted manipulation can defend models from adversarial threats. #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

💡 Shining a light on OOD. Hugo Lyons Keenan presents HALO, a robust detection method using joint optimization. Paper: arxiv.org/abs/2502.19755 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

🛑 Are we stuck in place? Matthieu Meeus lays out the state of membership inference on large models—and how to make real progress. #SaTML25

010

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

⚙️ Hyperparameters matter. Gauri Pradhan shows how tweaks under the hood change the strength of score-based membership inference. Paper: arxiv.org/abs/2502.06374 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

📊 Narrowing the scope. Jiashu Tao presents range membership inference attacks. Paper: arxiv.org/abs/2408.05131 #SaTML25

000

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

⚖️ Just because it looks like your data… Jie Zhang argues that membership inference attacks fall short of proving actual training inclusion. Paper: arxiv.org/abs/2409.19798 #SaTML25

031

Conference on Secure and Trustworthy Machine Learning @satml.org · 10/04/2025

☀️ Good morning from #SaTML25 Day 2! We’re starting with a keynote on privacy, memorization, and how we measure what models remember. Kamalika Chaudhuri takes the stage with The Science of Empirical Privacy Measurement: Memorization and Beyond.

021

Conference on Secure and Trustworthy Machine Learning @satml.org · 09/04/2025

🎉 After a full day of talks and discussion, we’re closing Day 1 of #SaTML25 with the poster session and reception! Posters are up, snacks are out, and the conversations continue. See you there!

041

Conference on Secure and Trustworthy Machine Learning @satml.org · 09/04/2025

🧠 Memory isn’t just helpful—it’s risky. Chad DeChant argues that episodic memory in AI agents deserves more scrutiny. Paper: arxiv.org/abs/2501.11739 #SaTML25

010

Conference on Secure and Trustworthy Machine Learning @satml.org · 09/04/2025

🔒 Hardwired models? Eleanor Clifford talks about locking machine learning models into hardware. Paper: arxiv.org/abs/2405.20990 #SaTML25

010