arxiv
PublishedMay 28, 2026 at 4:00 AM
EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection
Publisher summary· verbatim
arXiv:2505.17654v4 Announce Type: replace-cross Abstract: E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading product content. However, these models remain vulnerable to evasive content, which refers to inputs that
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning12harxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning12harxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models12harxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents12hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗