Last analyzed 9/9/2026

Language Model Security Database

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

985 research findings · 1123 evaluated models

Findings

985

Models evaluated

1123

Paper-evaluated models

Any selected model can match.

Refine by category

Findings match every selected category.

Attack Type2 selected

Attack Context

Architecture Components1 selected

Attack Surface

Impact

Advanced filters

Published fromPublished through

Research indexed from arXiv.

Evidence status

Filtered research findings

2 entries

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

Mobile Agent Visual Spoofing

Published 2/1/2026

Analyzed 2/22/2026

Mobile Large Language Model (LLM) agents operating under the "Screen-as-Interface" paradigm are vulnerable to visual indirect prompt injection and state desynchronization. Agents that rely on unstructured visual data (screenshots) and Accessibility Service APIs to perceive the environment lack a mechanism to distinguish between trusted system UI elements and untrusted content (e.g., web pages, emails, or malicious overlays). An attacker can inject visual cues, fake notifications, or hidden…

Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System

Evaluated models: Not reported

Source: arXiv

JailFlip Implicit Harm

Published 6/1/2025

Analyzed 12/8/2025

A vulnerability exists in the safety alignment mechanisms of Large Language Models (LLMs) (including GPT-4, Claude 3, Gemini, and Qwen families) leading to "Implicit Harm." Unlike traditional jailbreaks that use overtly harmful queries, this vulnerability allows remote attackers to coerce the model into providing factually incorrect, plausible, and dangerous responses to benign-looking inputs. By employing "JailFlip" techniques—specifically constructed affirmative-type or denial-type queries…

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures

Evaluated models: GPT-4.1, GPT-4.1 Mini, GPT-4o +3 more

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.