Towards machine learning models robust to adversarial examples and backdoor attacks
In the past decade, machine learning spectacularly succeeded on many challenging benchmarks. However, are our machine learning models ready to leave this lab setting and be safely deployed in high-stakes real-world applications? In this thesis, we take steps towards making this vision a reality by d...
Main Author: | Makelov, Aleksandar |
---|---|
Other Authors: | Mądry, Aleksander |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2023
|
Online Access: | https://hdl.handle.net/1721.1/147387 |
Similar Items
-
Towards deep learning models resistant to adversarial attacks
by: Madry, A, et al.
Published: (2021) -
Robust Feature-Guided Generative Adversarial Network for Aerial Image Semantic Segmentation against Backdoor Attacks
by: Zhen Wang, et al.
Published: (2023-05-01) -
Backdoor Pony: Evaluating backdoor attacks and defenses in different domains
by: Arthur Mercier, et al.
Published: (2023-05-01) -
Backdoor Attack on Deep Learning Models:A Survey
by: YING Zonghao, WU Bin
Published: (2023-03-01) -
Spectral Signatures in Backdoor Attacks
by: Tran, Brandon, et al.
Published: (2021)