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 Context1 selected

Architecture Components1 selected

Attack Surface

Impact1 selected

Advanced filters

Published fromPublished throughSource or venue

arXiv is the only currently indexed source.

Evidence status

Filtered research findings

1 entry

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

Adversarial ROI Privacy Attack

Updated 12/30/2025

Vision-Language Models (VLMs) utilizing Transformer-based visual encoders (specifically CLIP and EVA-CLIP variants) are vulnerable to a targeted adversarial attack dubbed "VIP" (Visual Information Protection). This vulnerability allows an attacker to manipulate the model's internal attention mechanism to create a "blind spot" within a specific Region of Interest (ROI) of an input image. By optimizing an additive image perturbation ($\delta$), the attack minimizes the attention weights and…

VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models

Affects: InstructBLIP, Vicuna 7B

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.