Video-LLMs are increasingly deployed in safety-critical applications but are vulnerable to Energy-Latency Attacks (ELAs) that exhaust computational resources. Current image-centric methods fail because temporal aggregation mechanisms dilute individual frame perturbations. Additionally, real-time demands make instance-wise optimization impractical for continuous video streams. We introduce VidDoS, which is the first universal ELA framework tailored for Video-LLMs. Our method leverages universal optimization to create instance-agnostic triggers that require no inference-time gradient calculation. We achieve this through masked teacher forcing to steer models toward expensive target sequences, combined with a refusal penalty and early-termination suppression to override conciseness priors. Testing across three mainstream Video-LLMs and three video datasets, which include video question answering and autonomous driving scenarios, shows extreme degradation. VidDoS induces a token expansion of more than 205× and inflates the inference latency by more than 15× relative to clean baselines. Simulations of real-time autonomous driving streams further reveal that this induced latency leads to critical safety violations. We urge the community to recognize and mitigate these high-hazard ELA in Video-LLMs.
@article{arxiv.2603.01454,
title = {VidDoS: Universal Denial-of-Service Attack on Video-based Large Language Models},
author = {Duoxun Tang and Dasen Dai and Jiyao Wang and Xiao Yang and Jianyu Wang and Siqi Cai},
journal= {arXiv preprint arXiv:2603.01454},
year = {2026}
}