|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM377750735 |
| 003 |
DE-627 |
| 005 |
20250306161653.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240918s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2024.3458858
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1258.xml
|
| 035 |
|
|
|a (DE-627)NLM377750735
|
| 035 |
|
|
|a (NLM)39288044
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Yang, Xi
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Adapting Few-Shot Classification via In-Process Defense
|
| 264 |
|
1 |
|c 2024
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 26.09.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Most few-shot learning methods employ either adaptive approaches or parameter amortization techniques. However, their reliance on pre-trained models presents a significant vulnerability. When an attacker's trigger activates a hidden backdoor, it may result in the misclassification of images, profoundly affecting the model's performance. In our research, we explore adaptive defenses against backdoor attacks for few-shot learning. We introduce a specialized stochastic process tailored to task characteristics that safeguards the classification model against attack-induced incorrect feature extraction. This process functions during forward propagation and is thus termed an "in-process defense." Our method employs an adaptive strategy, effectively generating task-level representations, enabling rapid adaptation to pre-trained models, and proving effective in few-shot classification scenarios for countering backdoor attacks. We apply latent stochastic processes to approximate task distributions and derive task-level representations from the support set. This task-level representation guides feature extraction, leading to backdoor trigger mismatching and forming the foundation of our parameter defense strategy. Benchmark tests on Meta-Dataset reveal that our approach not only withstands backdoor attacks but also shows an improved adaptation in addressing few-shot classification tasks
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Kong, Dechen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Lin, Ren
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Nannan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Gao, Xinbo
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 33(2024) vom: 17., Seite 5232-5245
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnas
|
| 773 |
1 |
8 |
|g volume:33
|g year:2024
|g day:17
|g pages:5232-5245
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2024.3458858
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 33
|j 2024
|b 17
|h 5232-5245
|