ItemConference Paper

MVTamperBench: Evaluating Robustness of Vision-Language Models

Title
MVTamperBench: Evaluating Robustness of Vision-Language Models
Creator
Agarwal, Amit; Panda, Srikant; Charles, Angeline; Patel, Hitesh; Kumar, Bhargava; Pattnayak, Priyaranjan; Rafi, Taki Hasan; Kumar, Tejaswini; Meghwani, Hansa; Gupta, Karan; Chae, Dong-Kyu
Description
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 under-explored. To address this gap, we introduce 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 3.4K original videos, expanded into over 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. 2025 Association for Computational Linguistics.
Source
Proceedings of the Annual Meeting of the Association for Computational Linguistics;pp.18804-18828
Date
01-01-2025
Publisher
Association for Computational Linguistics (ACL)
Coverage
Agarwal A., Liverpool John Moores University, United Kingdom; Panda S., Birla Institute of Technology, India; Charles A., Christ University, India; Patel H., New York University, United States; Kumar B., Columbia University, United States; Pattnayak P., University of Washington, United States; Rafi T.H., Hanyang University, South Korea; Kumar T., Columbia University, United States; Meghwani H., Liverpool John Moores University, United Kingdom; Gupta K., New York University, United States; Chae D.-K., Hanyang University, South Korea
Rights
All Open Access; Gold Open Access
Relation
ISSN: 0736587X; ISBN: 979-889176256-5;
Format
online
Language
English
Type
Conference paper

Citation

Agarwal, Amit; Panda, Srikant; Charles, Angeline; Patel, Hitesh; Kumar, Bhargava; Pattnayak, Priyaranjan; Rafi, Taki Hasan; Kumar, Tejaswini; Meghwani, Hansa; Gupta, Karan; Chae, Dong-Kyu, “MVTamperBench: Evaluating Robustness of Vision-Language Models,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/26235.

Output Formats