Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learning

Researchers have discovered a new type of backdoor attack on vertical federated learning systems that doesn't require triggers, posing significant privacy risks even when attackers are only curious during training. This feature-based triggerless attack is highly effective and robust against various defenses, highlighting the need for improved security measures in federated learning environments.

Read the full article at arXiv cs.CR (Cryptography & Security)

---

Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.