Skip to main content

Glossary

LLM

Large Language Model — A type of AI model trained on vast amounts of text to understand and generate human-like language, underpinning tools like chatbots and coding assistants. LLMs introduce novel security risks distinct from traditional software, including prompt injection, data leakage through model outputs, and hallucinated but confidently stated false information.

Recent coverage mentioning LLM

INFO
Threat Intel

GTIG AI Threat Tracker: Evolution of Adversarial Agentic AI

Google Threat Intelligence Group tracks threat actors shifting to agentic AI, targeting proprietary models, and abusing open source software.

Runtime Rebel Intel
4 min read · Sep 8, 2026
HIGH
Vulnerabilities

LLM API Vulnerability: Stealing AI Reasoning Traces

A critical architectural flaw in proprietary LLM APIs enables extraction of AI reasoning traces, PII, and credentials, also allowing invisible prompt injections.

Runtime Rebel Intel
4 min read · Sep 8, 2026
The AI Safety Penalty: How LLM Guardrails Hinder Defenders
INFO
Threat Intel

The AI Safety Penalty: How LLM Guardrails Hinder Defenders

Cisco Talos warns about the 'AI safety penalty,' where large language model guardrails impede legitimate defensive operations, giving attackers an advantage.

Runtime Rebel Intel
4 min read · Sep 3, 2026
AI-Assisted Campaigns Target Latin American Organizations
HIGH
Threat Intel

AI-Assisted Campaigns Target Latin American Organizations

Ongoing multi-stage network intrusions and data exfiltration campaigns in Latin America leverage AI tools to enhance operations.

Runtime Rebel Intel
4 min read · Sep 3, 2026
HIGH
Threat Intel

Rogue LLM Endpoints: Data Exposure & RCE Risk for AI Agents

Unverified LLM endpoints pose significant risks, enabling data leakage and potential remote code execution via compromised AI agent sessions.

Runtime Rebel Intel
4 min read · Sep 1, 2026
Diagnosing LLM Safety Fragility with Perturbation Probing
INFO
Threat Intel

Diagnosing LLM Safety Fragility with Perturbation Probing

New research introduces Perturbation Probing to diagnose LLM safety fragility, revealing guardrails are often concentrated in few neurons.

Runtime Rebel Intel
4 min read · Sep 1, 2026

Advertisement

← All 285 glossary terms