Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks

Wenhan Yang; Jingdong Gao; Baharan Mirzasoleiman

2024 ICML ICML 2024

Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Wenhan Yang, Jingdong Gao, Baharan Mirzasoleiman

Topics

Artificial Intelligence > Core AI > AI Safety Artificial Intelligence > Core AI > Multimodal Learning Machine Learning > Learning Types > Adversarial Learning

Keywords

contrastive learning backdoor attack gaussian mixture model cosine similarity targeted data poisoning clip

Download PDF