Defense MEDIUM relevance

Comparative Analysis of Inference-Time Defense Methods for Multimodal Large Language Models

Bulat Nutfullin Vladimir Evgrafov Dmitry Namiot
Published
June 9, 2026
Updated
June 9, 2026

Abstract

Multimodal large language models (MLLMs) now appear in safety-critical applications, but the visual channel leaves them open to adversarial attacks that predominantly text-oriented safety alignment addresses only in part. Retraining a model for each new vulnerability class is usually too expensive to be practical. We report a comparative empirical evaluation of three inference-time defense methods and their combinations, run on eight models from the InternVL and Qwen-VL families across seven safety benchmarks that span four attack classes and total 9,000 evaluation samples. Every figure below comes from the same unified proxy classifier. Five findings emerge from the evaluation. First, within the evaluated models and benchmarks, no single defense dominates across all settings: what works depends on the model's baseline safety and on the attack type. Second, combining defenses directly drives benign-query over-refusal to 97-100% across all eight evaluated models, and SmoothVLM on its own reaches 99.2-100%. Third, a simple safety prompt keeps utility largely intact (0.0-18.2% over-refusal across all eight models, five of them below 7%, although two exceeded 15%) while still yielding moderate safety gains. Fourth, different attack classes expose different weaknesses across the evaluated setup, which is why multi-benchmark evaluation matters. Fifth, in a preliminary whitebox test on two models (n=20), text-level defenses suppressed a PGD visual attack that had succeeded without any defense: the defenses act at the output stage, where gradient optimization has limited direct leverage in the tested configuration. Read together, these results argue for adaptive defense selection rather than a single fixed defense configuration.

Pro Analysis

Full threat analysis, ATLAS technique mapping, compliance impact assessment (ISO 42001, EU AI Act), and actionable recommendations are available with a Pro subscription.

Threat Deep-Dive
ATLAS Mapping
Compliance Reports
Actionable Recommendations
Start 14-Day Free Trial