Search Results for author:
Found 4 papers, 1 papers with code
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning
However, the security issues, e. g., Trojan attacks, of prompt tuning on a few data samples are not well-studied.
TrojFair: Trojan Fairness Attacks
TrojFair is a stealthy Fairness attack that is resilient to existing model fairness audition detectors since the model for clean inputs is fair.
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
We evaluated SSL-Cleanse on various datasets using 1200 encoders, achieving an average detection success rate of 82. 2% on ImageNet-100.
TrojViT: Trojan Insertion in Vision Transformers
The success of ViTs motivates adversaries to perform backdoor attacks on ViTs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
