DTA: distribution transform-based attack for query-limited scenario
In generating adversarial examples, the conventional black-box attack methods rely on sufficient feedback from the to-be-attacked models by repeatedly querying until the attack is successful, which usually results in thousands of trials during an attack. This may be unacceptable in real applications...
Main Authors: | Liu, Renyang, Zhou, Wei, Jin, Xin, Gao, Song, Wang, Yuanyu, Wang, Ruxin |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Journal Article |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/179697 |
Similar Items
-
Adversarial attacks and robustness for segment anything model
by: Liu, Shifei
Published: (2024) -
Targeted universal adversarial examples for remote sensing
by: Bai, Tao, et al.
Published: (2023) -
Minimalistic attacks : how little it takes to fool deep reinforcement learning policies
by: Qu, Xinghua, et al.
Published: (2021) -
Deep-attack over the deep reinforcement learning
by: Li, Yang, et al.
Published: (2022) -
PLL to the Rescue: A Novel EM Fault Countermeasure
by: Miura, Noriyuki, et al.
Published: (2016)