@inproceedings{agarwal-etal-2025-mvtamperbench,
    title = "{MVT}amper{B}ench: Evaluating Robustness of Vision-Language Models",
    author = "Agarwal, Amit  and
      Panda, Srikant  and
      Charles, Angeline  and
      Patel, Hitesh Laxmichand  and
      Kumar, Bhargava  and
      Pattnayak, Priyaranjan  and
      Rafi, Taki Hasan  and
      Kumar, Tejaswini  and
      Meghwani, Hansa  and
      Gupta, Karan  and
      Chae, Dong-Kyu",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.963/",
    pages = "18804--18828",
    ISBN = "979-8-89176-256-5",
    abstract = "Multimodal Large Language Models (MLLMs), are recent advancement of Vision-Language Models (VLMs) that have driven major advances in video understanding. However, their vulnerability to adversarial tampering and manipulations remains underexplored. To address this gap, we introduce \textbf{MVTamperBench}, a benchmark that systematically evaluates MLLM robustness against five prevalent tampering techniques: rotation, masking, substitution, repetition, and dropping; based on real-world visual tampering scenarios such as surveillance interference, social media content edits, and misinformation injection. MVTamperBench comprises {\textasciitilde}3.4K original videos, expanded into over {\textasciitilde}17K tampered clips covering 19 distinct video manipulation tasks. This benchmark challenges models to detect manipulations in spatial and temporal coherence. We evaluate 45 recent MLLMs from 15+ model families. We reveal substantial variability in resilience across tampering types and show that larger parameter counts do not necessarily guarantee robustness. MVTamperBench sets a new benchmark for developing tamper-resilient MLLM in safety-critical applications, including detecting clickbait, preventing harmful content distribution, and enforcing policies on media platforms. We release all code, data, and benchmark to foster open research in trustworthy video understanding."
}