Vision language models reveal new clues to spot adversarial images
Detecting Adversarial Images through Response Profiles of Vision-Language Models
Computer Vision and Pattern Recognition
Summary
Adversarial images are specially altered pictures designed to trick AI models into making wrong predictions without looking suspicious. The authors found that by looking at how a frozen vision-language model responds to many different text prompts, they can detect these tricky images better. Their method creates a summary of these responses and uses a simple classifier to decide if an image is adversarial. This technique works well on various attacks and even when facing attacks it hasn't seen before.
What this means in practice
- •For security teams in ai companies: Enhance AI security by detecting manipulated images that try to mislead frozen vision-language models using response patterns to multiple semantic prompts.
- •For automated content moderation teams: Identify adversarial attempts to fool image classifiers by analyzing how images interact with different text prompts in frozen vision-language models.
Authors
Arash Vashagh, Roozbeh Razavi-Far
Abstract
Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity patterns seemingly plausible. We investigate whether we can identify adversarial inputs based on the broader way an image interacts with a collection of general semantic prompts. Our detector summarizes these responses using category-level statistics, relationships among prompts, deviations from clean reference distributions, and stability under weak image transformations, producing a compact response profile that is classified by a lightweight model while the VLM remains fixed. We evaluate the approach on multiple public image datasets, several CLIP-style visual backbones, and a range of gradient-based, optimization-based, automated, and spatial attacks. The detector achieves strong discrimination in attack-specific settings and retains substantial performance when evaluated on attacks not seen during training. Under a controlled detector-specific protocol, the response-profile representation outperforms the evaluated embedding-geometry baselines. Additional analyses show that the feature groups provide complementary information and that the method remains effective under variations in the prompt configuration. We also examine inference cost and performance against detector-aware adaptive attacks. Overall, the results indicate that response patterns across semantic prompts provide a useful complementary signal for adversarial image detection in frozen VLMs.