37:55
Amrita Roy Chowdhury (UCSD), EIFFeL: Ensuring Integrity for Federated Learning
47:11
Xudong Pan (Fudan U.), The Security Pitfalls of DNN Watermarking Algorithms under Neural Obfuscation
46:17
Yizheng Chen (U of Maryland), Continuous Learning for Android Malware Detection
42:24
Christian Wressnegger (KIT), Explanation-Aware Attacks against Neural Networks
32:37
Not what you’ve signed up for: Investigating the Security of LLM-Integrated Applications
44:38
Jingxuan He (ETH) -- Controlling Pretrained Language Models to Generate Secure and Vulnerable Code
52:46
Jinyuan Jia (UIUC) - Machine Learning Meets Security and Privacy: Opportunities and Challenges
42:53
Shawn Shan, Security beyond Defenses: Protecting DNN systems via Forensics and Recovery
48:38
Wenbo Guo (UC Berkeley), Strengthening and Enriching Machine Learning for Cybersecurity
48:48
Ahmed Salem (Microsoft Research), Adversarial Exploration of Machine Learning Models' Accountability
50:27
Xuechen Li, Some Recent Developments in Differentially Private Deep Learning
49:25
Varun Chandrasekaran, Interdisciplinary Research Yields New Insights: A Case-Study in Privacy & ML
49:27
Matthew Jagielski (Google Research), Some Results on Privacy and Machine Unlearning
43:05
Tianhao Wang (University of Virginia), Continuous Release of Data Streams under Differential Privacy
59:35
Jamie Hayes (DeepMind), Towards Transformation-Resilient Provenance Detection
55:31
Jacob Steinhardt (UC Berkeley), The Science of Measurement in Machine Learning
01:11:19
Alina Oprea, Machine Learning Integrity and Privacy in Adversarial Environments
43:02
Bristena Oprisanu, Synthetic Data - A Privacy Mirage?
54:12
Nicolas Papernot, What does it mean for ML to be trustworthy?
42:27
Graham Cormode, Towards Federated Analytics with Local Differential Privacy
42:46
Vitaly Shmatikov, How to Salvage Federated Learning
X
About
Videos of research seminars broadly on the topic of Privacy and Security in Machine Learning (PriSec-ML)
prisec-ml.github.io
Tags