Huiying Li

Affiliations:
  • University of Chicago, Department of Computer Science, Chicago, IL, USA (PhD 2023)


According to our database1, Huiying Li authored at least 12 papers between 2019 and 2022.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2022
Can Backdoor Attacks Survive Time-Varying Models?
CoRR, 2022

Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks.
Proceedings of the 31st USENIX Security Symposium, 2022

2020
Blacklight: Defending Black-Box Adversarial Attacks on Deep Neural Networks.
CoRR, 2020

Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models.
CoRR, 2020

Fawkes: Protecting Privacy against Unauthorized Deep Learning Models.
Proceedings of the 29th USENIX Security Symposium, 2020

Demonstrating Wearable Microphone Jamming.
Proceedings of the Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, 2020

Wearable Microphone Jamming.
Proceedings of the CHI '20: CHI Conference on Human Factors in Computing Systems, 2020

2019
Persistent and Unforgeable Watermarks for Deep Neural Networks.
CoRR, 2019

Regula Sub-rosa: Latent Backdoor Attacks on Deep Neural Networks.
CoRR, 2019

Understanding the Effectiveness of Ultrasonic Microphone Jammer.
CoRR, 2019

Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks.
Proceedings of the 2019 IEEE Symposium on Security and Privacy, 2019

Latent Backdoor Attacks on Deep Neural Networks.
Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, 2019


  Loading...