REVIEW 6 cited by
Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content. Vision-language models (VLMs) stand at the forefront of this advancement, offering innovative ways to combine visual and textual data for enhanced understanding and interaction. However, this integration also enlarges the attack surface. Patch-based adversarial attack is considered the most realistic threat model in physical vision applications, as demonstrated in many existing literature. In this paper, we propose to address patched visual prompt injection, where adversaries exploit adversarial patches to generate target content in VLMs. Our investigation reveals that patched adversarial prompts exhibit sensitivity to pixel-wise randomization, a trait that remains robust even against adaptive attacks designed to counteract such defenses. Leveraging this insight, we introduce SmoothVLM, a defense mechanism rooted in smoothing techniques, specifically tailored to protect VLMs from the threat of patched visual prompt injectors. Our framework significantly lowers the attack success rate to a range between 0% and 5.0% on two leading VLMs, while achieving around 67.3% to 95.0% context recovery of the benign images, demonstrating a balance between security and usability.
Forward citations
Cited by 6 Pith papers
-
Devil in the Lens: Analyzing and Defending Physical Prompt Injection Against Vision-Language Models on Wearable Devices
Physical scene text can inject prompts into wearable VLMs, hijacking decisions and content with high success rates across six threat scenarios, partially mitigated by OCR masking and token-drift defenses.
-
Auditing Inference-Time Defense Evaluation for Multimodal Large Language Models
Stacking inference-time defenses for multimodal LLMs drives 97–100% over-refusal of benign queries; no single defense dominates and a simple prompt is often preferable.
-
Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding
Steganographic prompt injection is reported to covertly manipulate vision-language models with up to 31.8% success, but the evidence is not reproducible.
-
VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Models
VSF-Med introduces an eight-dimension, judge-scored vulnerability score for medical VLMs and reports that all five tested models are most vulnerable to persistent attack effects, with Llama-3.2 showing the largest drop.
-
Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack
A two-stage evaluation framework and token-projection analysis show that LVLMs encode harmful semantic cues from images even without OCR, while remaining vulnerable to cross-modal attacks.
-
A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
A survey of LVLM safety that adds a lifecycle taxonomy and new benchmark results showing Janus-Pro-7B has weaker safety than several open-source LVLMs.
Discussion (0). Continue with ORCID to comment.