DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain Fengpeng Li1 Kemou Li1 Haiwei Wu
–Neural Information Processing Systems
Recent studies show that adversarial attacks disproportionately impact the patterns within the phase of the sample's frequency spectrum--typically containing
Neural Information Processing Systems
Feb-18-2026, 12:14:48 GMT
- Country:
- Africa
- Ethiopia > Addis Ababa
- Addis Ababa (0.04)
- Rwanda > Kigali
- Kigali (0.04)
- Ethiopia > Addis Ababa
- Asia
- China
- Guangdong Province (0.04)
- Hong Kong (0.04)
- Macao (0.04)
- Middle East
- Israel (0.04)
- Jordan (0.04)
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- Myanmar > Tanintharyi Region
- Dawei (0.04)
- South Korea > Seoul
- Seoul (0.04)
- China
- Europe
- North America
- Canada
- Alberta > Census Division No. 15
- Improvement District No. 9 > Banff (0.04)
- British Columbia > Vancouver (0.04)
- Quebec > Montreal (0.04)
- Alberta > Census Division No. 15
- United States
- California
- Los Angeles County > Long Beach (0.14)
- Monterey County > Monterey (0.04)
- San Diego County > San Diego (0.04)
- Washington > King County
- Seattle (0.04)
- Virginia (0.04)
- Florida > Miami-Dade County
- Miami (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- Maryland > Baltimore (0.04)
- Texas > Dallas County
- Dallas (0.04)
- California
- Canada
- Africa
- Genre:
- Research Report > New Finding (0.48)
- Industry:
- Government > Military (0.36)
- Information Technology > Security & Privacy (0.36)
- Technology: