2 papers
cs.AI2025
Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
Jin Hu, Jiakai Wang, Linna Jing +6
Recently, semantically constrained adversarial examples (SemanticAE), which are directly generated from natural language instructions, have become a promising avenue for future res…
cs.LG2024
Behavior Backdoor for Deep Learning Models
Jiakai Wang, Pengfei Zhang, Renshuai Tao +5
The various post-processing methods for deep-learning-based models, such as quantification, pruning, and fine-tuning, play an increasingly important role in artificial intelligence…