Chanhui Lee, Yeonghwan Song
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Data-free Universal Adversarial Perturbation (UAP) is an image-agnostic adversarial attack that deceives deep neural networks using a single perturbation generated solely from random noise without relying on data priors. However, traditional data-free UAP methods often suffer from limited transferability due to the absence of semantic content in random noise. To address this issue, we propose a novel data-free universal attack method that recursively extracts pseudo-semantic priors directly from the UAPs during training to enrich the semantic content within the datafree UAP framework. Our approach effectively leverages latent semantic information within UAPs via region sampling, enabling successful input transformations-typically ineffective in traditional data-free UAP methods due to the lack of semantic cues-and significantly enhancing blackbox transferability. Furthermore, we introduce a sample reweighting technique to mitigate potential imbalances from random sampling and transformations, emphasizing hard examples less affected by the UAPs. Comprehensive experiments on ImageNet show that our method achieves state-of-the-art performance in average fooling rate by a substantial margin, notably improves attack transferability across various CNN architectures compared to existing data-free UAP methods, and even surpasses data-dependent UAP methods. Code is available at: https://github. com/ChnanChan/PSP-UAP.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2502.21048")
get_code_for_paper("2502.21048")
have("2502.21048")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2502.21048.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2502.21048)
Connect an agent — have() is free.