कवर छवि

Backdoor Attacks against Learning-Based Algorithms

This book introduces a new type of data poisoning attack, dubbed, backdoor attack. In backdoor attacks, an attacker can train the model with poisoned data to obtain a model that performs well on a normal input but behaves wrongly with crafted triggers. Backdoor attacks can occur in many scenarios wh...

पूर्ण विवरण

में बचाया:
ग्रंथसूची विवरण
मुख्य लेखकों: Li, Shaofeng (लेखक), Zhu, Haojin (लेखक), Wu, Wen (लेखक), Shen, Xuemin (Sherman) (लेखक)
निगमित लेखक: SpringerLink (Online service)
स्वरूप: इलेक्ट्रोनिक ई-पुस्तक
भाषा:अंग्रेज़ी
प्रकाशित: Cham : Springer Nature Switzerland : Imprint: Springer, 2024.
संस्करण:1st ed. 2024.
श्रृंखला:Wireless Networks,
विषय:
Computer networks .
Wireless communication systems.
Mobile communication systems.
Machine learning.
Computer Communication Networks.
Wireless and Mobile Communication.
Machine Learning.
ऑनलाइन पहुंच:https://doi.org/10.1007/978-3-031-57389-7
टैग: टैग जोड़ें
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
विषय - सूची:
  • Introduction
  • Literature Review of Backdoor Attacks
  • Invisible Backdoor Attacks in Image Classification Based Network Services
  • Hidden Backdoor Attacks in NLP Based Network Services
  • Backdoor Attacks and Defense in FL
  • Summary and Future Directions.

समान संसाधन