T
Timothy Tsai
Researcher at Nvidia
Publications - 49
Citations - 3218
Timothy Tsai is an academic researcher from Nvidia. The author has contributed to research in topics: Fault injection & Fault tolerance. The author has an hindex of 24, co-authored 49 publications receiving 2632 citations. Previous affiliations of Timothy Tsai include Alcatel-Lucent & Bell Labs.
Papers
More filters
Posted Content
Kayotee: A Fault Injection-based System to Assess the Safety and Reliability of Autonomous Vehicles to Faults and Errors.
Saurabh Jha,Timothy Tsai,Siva Kumar Sastry Hari,Michael J. Sullivan,Zbigniew Kalbarczyk,Stephen W. Keckler,Ravishankar K. Iyer +6 more
TL;DR: Kayotee is a fault injection-based tool to systematically inject faults into software and hardware components of the ADS to assess the safety and reliability of AVs to faults and errors, and an ontology model to characterize errors and safety violations impacting reliability and safety ofAVs is proposed.
Patent
Method for understanding and testing third party software components
TL;DR: In this article, a software wrapping technology is utilized to encase the COTS software components such that a wrapper isolates the cOTS components during testing, which is called software wrapping technique.
Posted Content
ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection
Saurabh Jha,Subho S. Banerjee,Timothy Tsai,Siva Kumar Sastry Hari,Michael J. Sullivan,Zbigniew Kalbarczyk,Stephen W. Keckler,Ravishankar K. Iyer +7 more
TL;DR: In this paper, a machine learning-based fault injection engine, called DriveFI, was proposed to mine situations and faults that maximally impact AV safety, as demonstrated on two industry-grade AV technology stacks (from NVIDIA and Baidu).
Patent
Stateful and cross-protocol intrusion detection for voice over IP
TL;DR: In this article, a method for detecting intrusions that employ messages of two or more protocols is disclosed, which can be used to recognize a variety of VoIP-based intrusion attempts, such as call hijacking, BYE attacks, etc.
Posted Content
HarDNN: Feature Map Vulnerability Evaluation in CNNs
Abdulrahman Mahmoud,Siva Kumar Sastry Hari,Christopher W. Fletcher,Sarita V. Adve,Charbel Sakr,Naresh R. Shanbhag,Pavlo Molchanov,Michael J. Sullivan,Timothy Tsai,Stephen W. Keckler +9 more
TL;DR: HarDNN is presented, a software-directed approach to identify vulnerable computations during a CNN inference and selectively protect them based on their propensity towards corrupting the inference output in the presence of a hardware error.