SmoothGuard: Defending Multimodal Large Language Models with Noise Perturbation and Clustering Aggregation
Multimodal large language models (MLLMs) have achieved impressive performance across diverse tasks by jointly reasoning over textual and visual inputs. Despite their success, these models remain highly vulnerable to adversarial manipulations, raising concerns about their safety and reliability in deployment. In this work, we first generalize an approach for generating adversarial images within the HuggingFace ecosystem and then introduce SmoothGuard, a lightweight and model-agnostic defense framework that enhances the robustness of MLLMs through randomized noise injection and clustering-based prediction aggregation. Our method perturbs continuous modalities (e.g., images and audio) with Gaussian noise, generates multiple candidate outputs, and applies embedding-based clustering to filter out adversarially influenced predictions. The final answer is selected from the majority cluster, ensuring stable responses even under malicious perturbations. Extensive experiments on POPE, LLaVA-Bench (In-the-Wild), and MM-SafetyBench demonstrate that SmoothGuard improves resilience to adversarial attacks while maintaining competitive utility. Ablation studies further identify an optimal noise range (0.1-0.2) that balances robustness and utility.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model
The rapid advancement of Large Vision-Language Models (LVLMs) is increasingly accompanied by unauthorized scraping and training on multimodal web data, posing severe copyright and privacy risks to data owners. Existing c…
Ensemble LearningDefending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges
As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains. In such an ML-equipped inference at…
BIG-bench Machine LearningInference AttackTest-Time Backdoor Attacks on Multimodal Large Language Models
Backdoor attacks are commonly executed by contaminating training data, such that a trigger can activate predetermined harmful effects during the test phase. In this work, we present AnyDoor, a test-time backdoor attack a…
Backdoor AttackAdvancing the Robustness of Large Language Models through Self-Denoised Smoothing
Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns. However, the increasing siz…
Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models
Fine-tuning pre-trained Vision-Language Models (VLMs) has shown remarkable capabilities in medical image and textual depiction synergy. Nevertheless, many pre-training datasets are restricted by patient privacy concerns,…