Next seminar Wed, June 15th, 2 PM (London time) Prof. Ben Y. Zhao (Ben Zhao, University of Chicago) "Adversarial Robustness via Forensics in Deep Neural Networks" Details: prisec-ml.github.io

Virtual Seminar, today (Wed) @ 2 PM UK time Prof. Ben Y. Zhao (Ben Zhao, University of Chicago) "Adversarial Robustness via Forensics in Deep Neural Networks" Details: prisec-ml.github.io

The IT University Copenhagen and Aarhus University are organizing a Summer School on Privacy-Preserving Machine Learning that will be held from the 1st of August until the 4th of August in Copenhagen, Denmark. HT Carsten Baum conferencemanager.dk/ppmlschool2022

📢Tomorrow, July 12th, 1:30PM (UK time)📢 Soham De & Leonard Berrada (DeepMind), Unlocking High-Accuracy Differentially Private Image Classification through Scale Related tech repo: arxiv.org/abs/2204.13650 Details: prisec-ml.github.io

Yesterday's DeepMind seminar was our 30th since we started about 18 months ago. Thanks to all the speakers and attendees for making it special. Now time to sign off for a well-deserved summer break :-) See you in September! prisec-ml.github.io

1/5 Today, we launched U.K.🇬🇧 - U.S.🇺🇸 innovation prize challenges to advance privacy-enhancing technologies to tackle financial crime and public health emergencies. U.K. innovators have until 19 September to enter. Apply here: petsprizechallenges.com

Happy to share our paper led by Raymond “Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots” (arxiv.org/abs/2209.03463) is accepted by ACM CCS 2025, this is a great collaboration and #teameffort @emilianoucl Jeremy Blackburn Savvas Zannettou @gianluca_string Cispa (degen)

Summer is over and we are back! Next seminar Wed, September 28th, 3:30 PM (Central European Time) Prof. Tianhao Wang (Tianhao Wang, University of Virginia) "Continuous Release of Data Streams under Differential Privacy" Details: prisec-ml.github.io

The seminar will start in 40 mins!

Next seminar Wed, October 5th, 3:30 PM (Central European Time) Matthew Jagielski (Google Research) "Some Results on Privacy and Machine Unlearning" Details: prisec-ml.github.io

Next seminar Wed, October 26th, 3:30 PM (Central European Time) Varun Chandrasekaran (Microsoft Research) "Interdisciplinary Research Yields New Insights: A Case-Study in Privacy & ML" Details: prisec-ml.github.io

Next seminar Wed, November 9th (Today), 3:30 PM (Central European Time) Xuechen Li (Stanford University) Xuechen Li "Some Recent Developments in Differentially Private Deep Learning" Details: prisec-ml.github.io

Next seminar Wed, December 6th (tomorrow), 3:30 PM (Central European Time) Ahmed Salem (Microsoft Research) Ahmed Salem "Adversarial Exploration of Machine Learning Models’ Accountability" prisec-ml.github.io

Next seminar Wed, March 22nd (tomorrow), 3:30 PM (Central European Time) Shawn Shan (University of Chicago) @shawnshan_ "Security beyond Defenses: Protecting DNN systems via Forensics and Recovery" Details: prisec-ml.github.io

Next seminar Wed, April 5th (today), 3:30 PM (Central European Time) Jinyuan Jia (UIUC) "Machine Learning Meets Security and Privacy: Opportunities and Challenges" Details: prisec-ml.github.io

Next seminar Wed, April 19th, 3:30 PM (Central European Time) Jingxuan He (ETH) "Controlling Pretrained Language Models to Generate Secure and Vulnerable Code" Details: prisec-ml.github.io

In the next months, I'll be looking forward to hiring 3 full-time PhD students in the topics of: - FL and Privacy - Individualized Privacy in ML - Private and Trustworthy ML Feel free to forward if you know anyone who is interested!

Next seminar Today, April 19th, 4:30 PM (Central European Time) Yizheng Chen (University of Maryland) Continuous Learning for Android Malware Detection Details: prisec-ml.github.io

Next seminar June 28th, 3:30 PM (Central European Time) Xudong Pan (Fudan University) The Security Pitfalls of DNN Watermarking Algorithms under Neural Obfuscation Details: prisec-ml.github.io

Next seminar July 12th, 3:30 PM (Central European Time) Amrita Roy Chowdhury (UCSD) EIFFeL: Ensuring Integrity for Federated Learning Details: prisec-ml.github.io