Conference on Secure and Trustworthy Machine Learning
@satml.org
IEEE Conference on Secure and Trustworthy Machine Learning
March 2026 (Munich) • #SaTML2026
https://satml.org/
March 2026 (Munich) • #SaTML2026
https://satml.org/
🔍 How private was that release? @a-h-koskela.bsky.social presents a method for auditing DP guarantees using density estimation. #SaTML25
April 11, 2025 at 2:24 PM
🔍 How private was that release? @a-h-koskela.bsky.social presents a method for auditing DP guarantees using density estimation. #SaTML25
🧮 Getting the math right. @matt19234.bsky.social walks through common traps in privacy accounting and how to avoid them. #SaTML25
April 11, 2025 at 2:12 PM
🧮 Getting the math right. @matt19234.bsky.social walks through common traps in privacy accounting and how to avoid them. #SaTML25
🧠 Marginals leak. Steven Golob shows how synthetic data built on marginals can still compromise privacy. Paper: arxiv.org/abs/2410.05506 #SaTML25
April 11, 2025 at 2:03 PM
🧠 Marginals leak. Steven Golob shows how synthetic data built on marginals can still compromise privacy. Paper: arxiv.org/abs/2410.05506 #SaTML25
📃🔐 Privacy and fairness? Khang Tran introduces FairDP, enabling fairness certification alongside differential privacy. Paper: arxiv.org/abs/2305.16474 #SaTML25
April 11, 2025 at 1:43 PM
📃🔐 Privacy and fairness? Khang Tran introduces FairDP, enabling fairness certification alongside differential privacy. Paper: arxiv.org/abs/2305.16474 #SaTML25
🖼️📡 Hide and seek. Luke Bauer presents a method for covert messaging with provable security via image diffusion. Paper: arxiv.org/abs/2503.10063 #SaTML25
April 11, 2025 at 1:11 PM
🖼️📡 Hide and seek. Luke Bauer presents a method for covert messaging with provable security via image diffusion. Paper: arxiv.org/abs/2503.10063 #SaTML25
💣 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
April 11, 2025 at 12:53 PM
💣 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
📊 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
April 11, 2025 at 12:03 PM
📊 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
📚🔒 Choose wisely. Kristian Schwethelm presents a method to balance data utility and privacy in active learning. Paper: arxiv.org/abs/2410.00542 #SaTML25
April 11, 2025 at 11:49 AM
📚🔒 Choose wisely. Kristian Schwethelm presents a method to balance data utility and privacy in active learning. Paper: arxiv.org/abs/2410.00542 #SaTML25
⚖️ 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
April 11, 2025 at 11:32 AM
⚖️ 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
🌲💀 Even decision trees aren’t safe. Lorenzo Cazzaro shows how to poison tree-based models. Paper: arxiv.org/abs/2410.00862 #SaTML25
April 11, 2025 at 9:59 AM
🌲💀 Even decision trees aren’t safe. Lorenzo Cazzaro shows how to poison tree-based models. Paper: arxiv.org/abs/2410.00862 #SaTML25
🚗🔦 How robust are LiDAR detectors?Alexandra Arzberger presents Hi-ALPS, benchmarking six systems used in autonomous vehicles. Paper: arxiv.org/abs/2503.17168 #SaTML25
April 11, 2025 at 9:41 AM
🚗🔦 How robust are LiDAR detectors?Alexandra Arzberger presents Hi-ALPS, benchmarking six systems used in autonomous vehicles. Paper: arxiv.org/abs/2503.17168 #SaTML25
🎯 Robustness meets domain adaptation. Natalia Ponomareva introduces DART, a principled method for adapting without labels—and withstanding attacks. #SaTML25
April 11, 2025 at 9:24 AM
🎯 Robustness meets domain adaptation. Natalia Ponomareva introduces DART, a principled method for adapting without labels—and withstanding attacks. #SaTML25
🌍 No central authority, no problem?Sayan Biswas explores fairness challenges and solutions in decentralized learning systems. Paper: arxiv.org/abs/2410.02541 #SaTML25
April 11, 2025 at 8:10 AM
🌍 No central authority, no problem?Sayan Biswas explores fairness challenges and solutions in decentralized learning systems. Paper: arxiv.org/abs/2410.02541 #SaTML25
☀️ 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.
April 11, 2025 at 7:08 AM
☀️ 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.
🌈 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
April 10, 2025 at 3:35 PM
🌈 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
🪵🧵 Texture vs. shape. Blaine Hoak dives into real-world evidence of texture bias in vision models. Paper: arxiv.org/abs/2412.10597 #SaTML25
April 10, 2025 at 3:20 PM
🪵🧵 Texture vs. shape. Blaine Hoak dives into real-world evidence of texture bias in vision models. Paper: arxiv.org/abs/2412.10597 #SaTML25
📎 Perception with CLIP. Christian Schlarmann shows how robustness in CLIP models improves perceptual metrics. Paper: arxiv.org/abs/2502.11725 #SaTML25
April 10, 2025 at 3:02 PM
📎 Perception with CLIP. Christian Schlarmann shows how robustness in CLIP models improves perceptual metrics. Paper: arxiv.org/abs/2502.11725 #SaTML25
🎯 Not all queries are equal. Lorenz Wolf presents a mechanism for private selection under varying sensitivity levels. Paper: arxiv.org/abs/2501.05309 #SaTML25
April 10, 2025 at 2:17 PM
🎯 Not all queries are equal. Lorenz Wolf presents a mechanism for private selection under varying sensitivity levels. Paper: arxiv.org/abs/2501.05309 #SaTML25
🔗 When noise talks. Haewon Jeong explores how correlated privacy can improve distributed mean estimation. Paper: arxiv.org/abs/2407.03289 #SaTML25
April 10, 2025 at 2:02 PM
🔗 When noise talks. Haewon Jeong explores how correlated privacy can improve distributed mean estimation. Paper: arxiv.org/abs/2407.03289 #SaTML25
📊 Stream, count, forget (privately). Rasmus Pagh presents a binning-based method for continual private counting. Paper: arxiv.org/abs/2412.07093 #SaTML25
April 10, 2025 at 1:47 PM
📊 Stream, count, forget (privately). Rasmus Pagh presents a binning-based method for continual private counting. Paper: arxiv.org/abs/2412.07093 #SaTML25
📱🛡️ 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
April 10, 2025 at 1:15 PM
📱🛡️ 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