Updated 7/21/2026

Language Model Security Database

Explore primary-source AI security research, evaluated models, attack techniques, and defensive evidence.

959 research findings · 1077 evaluated models

Findings

959

Models evaluated

1077

Paper-evaluated models

Any selected model can match.

Refine by category

Findings match every selected category.

Attack Type

Attack Context2 selected

Architecture Components

Attack Surface

Impact

Advanced filters

Published fromPublished throughSource or venue

arXiv is the only currently indexed source.

Evidence status

Filtered research findings

81 entries

Matches every word across titles, descriptions, sources, affected systems, and models.

Visual Jailbreak of LLMs

Updated 12/29/2024

A vulnerability in vision-integrated Large Language Models (VLMs) allows an attacker to circumvent safety mechanisms through the use of adversarially crafted visual examples. A single, carefully constructed image can universally "jailbreak" the model, causing it to generate harmful content in response to a wide range of subsequent prompts, even those not included in the adversarial example's training data. This vulnerability extends beyond simple misclassification to encompass the execution of…

Visual adversarial examples jailbreak large language models

Affects: InstructBLIP, MiniGPT-4

Source: arXiv

Research methodology

Entries summarize publicly available primary-source security research. Model names reflect only systems explicitly evaluated by the cited paper, and measurements are research-reported unless independent verification is stated.