Backdoor Attacks on Machine Learning with Covert False Data Injection-Part B: Tests

Based on the content of Part A [11], in this paper, we conduct the FDI attack test based on the modeling. The test mainly focuses on backdoor attacks under two modes of partial FDI and full FDI, respectively, and we introduce compound evaluation metrics to assess the effectiveness of the attacks and...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE Conference on Industrial Electronics and Applications (Online) s. 1 - 6
Hlavní autori: Liu, Charles Z., Cheng, Dawei, Zhang, Ying, Qin, Lu
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 03.08.2025
Predmet:
Accuracy
Adversarial machine learning
AI Security
Attack Concealment in AI
Backdoor Attacks
Clandestine Fraudulence
Clean Label Attack
Compounds
Data models
False Data Injection
Induced Model Attack
Industrial electronics
Machine learning algorithms
Machine Learning Vulnerabilities
Measurement
Security
System performance
Training
ISSN:2158-2297
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Based on the content of Part A [11], in this paper, we conduct the FDI attack test based on the modeling. The test mainly focuses on backdoor attacks under two modes of partial FDI and full FDI, respectively, and we introduce compound evaluation metrics to assess the effectiveness of the attacks and test the attacks against the three concealed FDI modes of adversarial backdoors. The experimental test results show that the proposed Clandestine Fraudulence is the most destructive to performance, while Clean Label Attack is the weakest, and Induced Model Attack has the best accuracy destruction concealment. This work can provide a basis for the security design of machine learning system attack and defense and training algorithms.
ISSN:2158-2297
DOI:10.1109/ICIEA65512.2025.11149083