Skip to main content
LLM Security Database
Skip to research search
Updated 7/21/2026, database is current

Language Model Security Database

959 research findings · 1077 evaluated models

Filtered research findings

2 entries

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

Physical Agent Object Misdirection

Updated 1/14/2026

AdvEDM reveals a vulnerability in Vision-Language Model (VLM) based Embodied Decision-Making (EDM) systems, such as those used in autonomous driving and robotic manipulation. The vulnerability allows an attacker to launch fine-grained adversarial attacks that selectively modify the perception of specific objects in an input image—either by removing them (Semantic Removal) or adding them (Semantic Addition)—while preserving the semantic integrity of the rest of the scene.

AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents
Affects: BLIP-2, MiniGPT-4, LLaVA-v2 +5 more

Source: arXiv

Model layer
Vision
Multimodal
Embedding

AD Black-Box Cascading Disruption

Updated 12/9/2025

Vision Language Models (VLMs) integrated into autonomous driving (AD) systems are vulnerable to a black-box adversarial attack method termed Cascading Adversarial Disruption (CAD). The vulnerability stems from the model's susceptibility to optimized visual perturbations that disrupt the decision-making reasoning chain (perception, prediction, and planning). Attackers can generate adversarial images or physical patches by aligning visual noise with deceptive textual semantics in the model's…

Black-box adversarial attack on vision language models for autonomous driving
Affects: GPT-4, GPT-4o, InstructBLIP

Source: arXiv

Model layer
Injection
Vision
Multimodal

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.