SmoothShift: Disrupting Visual Adversarial Attacks on LVLMs at Test Time

Visual adversarial perturbations can substantially impair large vision-language models (LVLMs) despite introducing only subtle input changes. To understand how these small changes cause substantial errors, we investigate their optimization and propagation through the model, revealing two key findings. First, stronger attacks rely on finer iterative optimization, while subtle input perturbations induce representation discrepancies that are amplified layer by layer through the vision encoder and persist in the language model. Second, disrupting the alignment between within-patch input patterns and the model's computation reduces clean-adversarial representation discrepancies and substantially weakens attacks. Together, these findings suggest that adversarial effectiveness depends on both fine-grained perturbation patterns and their coupling with the model's computation. Motivated by these findings, we propose SmoothShift, a lightweight, training-free defense that combines local smoothing and spatial transformations. Smoothing weakens fine-grained perturbation patterns, while spatial transformations disrupt their alignment with the encoder's patch grid. SmoothShift requires no model updates, auxiliary networks, or additional model inference. Experiments cover three LVLM families on four datasets and robustly fine-tuned Contrastive Language-Image Pre-training (CLIP) models on eight classification datasets. Evaluations across eight attack methods and multiple perturbation budgets demonstrate improved robustness while largely preserving clean performance. SmoothShift also provides robustness gains under defense-aware attacks using mixed-gradient BPDA with EOT.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20537
Primary Topic
Adversarial Robustness in Machine Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

SmoothShift: Disrupting Visual Adversarial Attacks on LVLMs at Test Time

Xiaoqing Chen, Dongrui Wu, Jiayi Ouyang
arXiv (Cornell University)
Adversarial Robustness in Machine Learning
preprint

SmoothShift: Disrupting Visual Adversarial Attacks on LVLMs at Test Time

Xiaoqing Chen, Dongrui Wu, Jiayi Ouyang
preprint en

Abstract

Visual adversarial perturbations can substantially impair large vision-language models (LVLMs) despite introducing only subtle input changes. To understand how these small changes cause substantial errors, we investigate their optimization and propagation through the model, revealing two key findings. First, stronger attacks rely on finer iterative optimization, while subtle input perturbations induce representation discrepancies that are amplified layer by layer through the vision encoder and persist in the language model. Second, disrupting the alignment between within-patch input patterns and the model's computation reduces clean-adversarial representation discrepancies and substantially weakens attacks. Together, these findings suggest that adversarial effectiveness depends on both fine-grained perturbation patterns and their coupling with the model's computation. Motivated by these findings, we propose SmoothShift, a lightweight, training-free defense that combines local smoothing and spatial transformations. Smoothing weakens fine-grained perturbation patterns, while spatial transformations disrupt their alignment with the encoder's patch grid. SmoothShift requires no model updates, auxiliary networks, or additional model inference. Experiments cover three LVLM families on four datasets and robustly fine-tuned Contrastive Language-Image Pre-training (CLIP) models on eight classification datasets. Evaluations across eight attack methods and multiple perturbation budgets demonstrate improved robustness while largely preserving clean performance. SmoothShift also provides robustness gains under defense-aware attacks using mixed-gradient BPDA with EOT.

arXiv (Cornell University)
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon