The Adversarial Implications of Variable-Time Inference

[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Towards an End-to-End (E2E) Adversarial Learning and Application in the Physical World

D Biton, J Shams, K Satoru, A Shabtai, Y Elovici… - arxiv preprint arxiv …, 2025 - arxiv.org
The traditional learning process of patch-based adversarial attacks, conducted in the digital
domain and then applied in the physical domain (eg, via printed stickers), may suffer from …
Save Cite Related articles All 2 versionsFree GPT-4 DeepSeek View as HTML