Showing 2025Show all
2 papers · 1 filter
cs.CV2025
FeatureFool: Zero-Query Fooling of Video Models via Feature Map
Duoxun Tang, Xi Xiao, Guangwu Hu +6
The vulnerability of deep neural networks (DNNs) has been preliminarily verified. Existing black-box adversarial attacks usually require multi-round interaction with the model and…
cs.CR2025
TextCrafter: Optimization-Calibrated Noise for Defending Against Text Embedding Inversion
Duoxun Tang, Xinhang Jiang, Jiajun Niu
Text embedding inversion attacks reconstruct original sentences from latent representations, posing severe privacy threats in collaborative inference and edge computing. We propose…