Category: AI Security

Articles tagged AI Security

Filters
Inside the loop: Five AI attack frameworks that never ask permission

Inside the loop: Five AI attack frameworks that never ask permission

Five agentic offensive frameworks act in bursts of two to 25 seconds, and none enforces authorization in code. What ARTEX, CyberStrikeAI, Cairn, PentAGI, and HexStrike leave in your telemetry, and the ES|QL hunt that catches them.

Mika Ayenson
56 AWS API calls in 141 milliseconds: Inside an AI-run intrusion

56 AWS API calls in 141 milliseconds: Inside an AI-run intrusion

A CyberStrikeAI server spent 16 days in four AWS accounts using eight identities, and the CloudTrail record shows why six detection rules each caught only part of it.

Samir Bousseaden
Auditing the auditor: Unmasking Apex Accelerator

Auditing the auditor: Unmasking Apex Accelerator

REF8801 exposes how Apex Accelerator combines convincing Web3 services with malicious npm packages, attacker-controlled AI infrastructure, and cross-platform malware delivery.

Jia Yu Chan
Living off the coding agent: Two tales of tunnels and LaunchAgents

Living off the coding agent: Two tales of tunnels and LaunchAgents

Agent-parented reverse tunnels and LaunchAgents can expose a local admin app to the internet. Endpoint still needs to treat that as high severity even when the activity looks like vibe-coded ops, not confirmed malware.

Mika Ayenson
The Cost of Understanding: LLM-Driven Reverse Engineering vs Iterative LLM Obfuscation

The Cost of Understanding: LLM-Driven Reverse Engineering vs Iterative LLM Obfuscation

Elastic Security Labs explores the ongoing arms race between LLM-driven reverse engineering and obfuscation.

Cyril François
MCP Tools: Attack Vectors and Defense Recommendations for Autonomous Agents

MCP Tools: Attack Vectors and Defense Recommendations for Autonomous Agents

This research examines how Model Context Protocol (MCP) tools expand the attack surface for autonomous agents, detailing exploit vectors such as tool poisoning, orchestration injection, and rug-pull redefinitions alongside practical defense strategies.

Carolina Beretta
Elastic Advances LLM Security with Standardized Fields and Integrations

Elastic Advances LLM Security with Standardized Fields and Integrations

Discover Elastic’s latest advancements in LLM security, focusing on standardized field integrations and enhanced detection capabilities. Learn how adopting these standards can safeguard your systems.

Mika Ayenson
Embedding Security in LLM Workflows: Elastic's Proactive Approach

Embedding Security in LLM Workflows: Elastic's Proactive Approach

Dive into Elastic's exploration of embedding security directly within Large Language Models (LLMs). Discover our strategies for detecting and mitigating several of the top OWASP vulnerabilities in LLM applications, ensuring safer and more secure AI-driven applications.

Mika Ayenson

Elastic Security Labs Newsletter