Last analyzed 8/13/2026

Language Model Security Database

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

969 research findings · 1102 evaluated models

Findings

969

Models evaluated

1102

Paper-evaluated models

Any selected model can match.

Refine by category

Findings match every selected category.

Attack Type

Attack Context

Architecture Components

Attack Surface

Impact1 selected

Advanced filters

Published fromPublished through

Research indexed from arXiv.

Evidence status

Filtered research findings

791 entries

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

Prompt Engineering Jailbreak

Published 5/1/2023

Analyzed 12/29/2024

Large Language Models (LLMs), specifically ChatGPT versions 3.5 and 4.0, are vulnerable to prompt engineering attacks that circumvent built-in content restrictions. Attackers can craft malicious prompts, categorized into "pretending," "attention shifting," and "privilege escalation" techniques, to elicit responses containing prohibited content (e.g., instructions for illegal activities, generation of harmful content). The vulnerability stems from the LLM's inability to reliably distinguish…

Jailbreaking chatgpt via prompt engineering: An empirical study

Evaluated models: GPT-3.5 Turbo, GPT-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.