Updated 3/9/2026
Video-based Large Language Models (Video-LLMs) are vulnerable to a universal Energy-Latency Attack (ELA) that triggers a Denial-of-Service (DoS) via spatially concentrated adversarial patches. Because video architectures rely on temporal subsampling and pooling which act as a low-pass filter against full-frame diffuse noise, an attacker can bypass this compression by anchoring cross-modal attention to a dense, localized visual anomaly. By injecting a fixed, content-agnostic patch into the…
VidDoS: Universal Denial-of-Service Attack on Video-based Large Language Models
Affects: LLaVA-NeXT-Video 7B, Qwen3-VL 4B Instruct, Video-LLaVA 7B
Source: arXiv