all AI news
Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferability
May 7, 2024, 4:48 a.m. | Juanjuan Weng, Zhiming Luo, Shaozi Li
cs.CV updates on arXiv.org arxiv.org
Abstract: Recent studies have shown that Deep Neural Networks (DNNs) are susceptible to adversarial attacks, with frequency-domain analysis underscoring the significance of high-frequency components in influencing model predictions. Conversely, targeting low-frequency components has been effective in enhancing attack transferability on black-box models. In this study, we introduce a frequency decomposition-based feature mixing method to exploit these frequency characteristics in both clean and adversarial samples. Our findings suggest that incorporating features of clean samples into adversarial features …
abstract adversarial adversarial attacks analysis arxiv attacks box components cs.cv domain feature improving low meta meta-learning networks neural networks predictions significance studies study targeting type via
More from arxiv.org / cs.CV updates on arXiv.org
Retrieval-Augmented Egocentric Video Captioning
2 days, 13 hours ago |
arxiv.org
Mirror-Aware Neural Humans
2 days, 13 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US