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 Type

Attack Context1 selected

Architecture Components

Attack Surface

Impact

Advanced filters

Published fromPublished through

Research indexed from arXiv.

Evidence status

Filtered research findings

11 entries

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

Sleeper Memory Poisoning in LLM Agents

Published 5/14/2026

Analyzed 7/20/2026

The paper presents a specific black-box indirect prompt-injection evaluation: attacker-controlled external content can cause a memory-enabled assistant or external memory manager to persist a fabricated user memory, which may later be retrieved in a separate session and steer responses or agent actions. The authors evaluate injection, retrieval, and conditional adversarial usage separately across synthetic document and future-session datasets. The released repository provides defensive…

Hidden in Memory: Sleeper Memory Poisoning in LLM Agents

Evaluated models: GPT-5.4, GPT-5.5, Claude Sonnet 4.6 +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.