Adversarial attacks and robustness for segment anything model
Segment Anything Model (SAM), as a potent graphic segmentation model, has demonstrated its application potential in various fields. Before deploying SAM in various applications, the robustness of SAM against adversarial attacks is a security concern that must be addressed. In this paper, we ex...
Main Author: | Liu, Shifei |
---|---|
Other Authors: | Jiang Xudong |
Format: | Final Year Project (FYP) |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/177032 |
Similar Items
-
Adversarial Attacks and Defense Technologies on Autonomous Vehicles: A Review
by: Mahima K. T. Y., et al.
Published: (2021-12-01) -
Robustness and Transferability of Adversarial Attacks on Different Image Classification Neural Networks
by: Kamilya Smagulova, et al.
Published: (2024-01-01) -
A Methodology for Evaluating the Robustness of Anomaly Detectors to Adversarial Attacks in Industrial Scenarios
by: Angel Luis Perales Gomez, et al.
Published: (2022-01-01) -
CANARY: An Adversarial Robustness Evaluation Platform for Deep Learning Models on Image Classification
by: Jiazheng Sun, et al.
Published: (2023-08-01) -
Structure Estimation of Adversarial Distributions for Enhancing Model Robustness: A Clustering-Based Approach
by: Bader Rasheed, et al.
Published: (2023-10-01)