On the Adversarial Robustness of Deep Learning

Channel:
Microsoft Research
Subscribers:
343,000
Published on ● Video Link: https://www.youtube.com/watch?v=YgYiECAr9Gs


Duration: 39:50
466 views
8

Research Talk
Jun Zhu, Tsinghua University 

Although deep learning methods have obtained significant progress in many tasks, it has been widely recognized that the current methods are vulnerable to adversarial noise. This weakness poses serious risk to safety-critical applications. In this talk, I will present some recent progress on adversarial attack and defense for deep learning, including theory, algorithms and benchmarks.

Learn more about the Responsible AI Workshop: https://www.microsoft.com/en-us/research/event/responsible-ai-an-interdisciplinary-approach-workshop/

This workshop was part of the Microsoft Research Summit 2022: https://www.microsoft.com/en-us/research/event/microsoft-research-summit-2022/



Other Videos By Microsoft Research


2022-12-12End-to-end Reinforcement Learning for the Large-scale Traveling Salesman Problem
2022-12-12Deep Reinforcement Learning in Supply Chain Optimizations
2022-12-12Inverse Game Theory for Stackelberg Games: The Blessing of Bounded Rationality
2022-12-06Personality Predictions from Automated Video Interviews: Explainable or Unexplainable Models?
2022-12-06Responsible AI: An Interdisciplinary Approach | Panel Discussion
2022-12-06Personalizing Responsibility within AI Systems: A Case for Designing Diversity
2022-12-06Evidence-based Evaluation for Responsible AI
2022-12-06Towards Trustworthy Recommender Systems: From Shallow Models to Deep Models to Large Models
2022-12-06Development of a Game-Based Assessment to Measure Creativity
2022-12-06Interpretability, Responsibility and Controllability of Human Behaviors
2022-12-06On the Adversarial Robustness of Deep Learning
2022-12-06The Long March Towards AI Fairness
2022-12-06Towards Human Value Based Natural Language Processing (NLP)
2022-12-06Responsible AI Research at Microsoft Research Asia
2022-12-06Responsible AI Workshop | Opening Remarks
2022-12-06Low-latency, Real-time Insights from Space
2022-12-06Next Generation Networking and its Platform Workshop | Panel Discussion
2022-12-06OpenNetLab: An Open Platform for RL-based Congestion Control for Real-Time Communication
2022-12-06Enhance Networking Education with OpenNetLab
2022-12-06Coping with High Mobility for Beyond 5G Cellular Networks
2022-12-06Reconfigurable Metamaterial Surfaces for mmWave and Satellite Networks