AI attack server

MCP Security Notification: Tool Poisoning Attacks

What is a Tool Poisoning Attack (TPA)? MCP tool poisoning attacks can hijack the agent''s behavior and exfiltrate

Web LLM attacks | Web Security Academy

AI-powered scanner vulnerabilities AI-powered web application scanners introduce a new attack surface. When scanner behavior

Agentjacking Attack Tricks AI Coding Agents Into Running Malicious

Researchers warn Agentjacking can abuse Sentry errors to make AI coding agents run malicious code on developer

Hacker uses DeepSeek AI to autonomously attack vulnerable servers

A Chinese-speaking threat actor is using the DeepSeek AI model and the open-source Hermes Agent to conduct

AI Cyberattacks: How attackers target AI, and use AI against you

AI cyberattacks are threats that either target AI systems –models, pipelines, agents, APIs, and the sensitive data

Can AI Attack the Cloud? Lessons From Building an Autonomous

Unit 42 reveals how multi-agent AI systems can autonomously attack cloud environments. Learn critical insights and

New Agentjacking Attack Hijacks Your AI Coding Agent to Run Code

Reportedly characterized the underlying class of attack as “not technically defensible” at the ingestion layer, instead

OpenAI says AI models went rogue during testing, triggering

OpenAI said on Tuesday that an autonomous agent powered by its advanced artificial intelligence models went rogue

LLMjacking: what these attacks are, and how to protect AI servers

An analysis of attacks on Ollama, LM Studio, AutoGPT, and LangServe servers, and recommendations on protecting

Chinese hacker used DeepSeek to launch autonomous cyberattacks

A Chinese threat actor used DeepSeek and Hermes Agent to run autonomous cyberattacks against internet-facing

What is an AI attack? An overview on AI Attack by Iterasec

Dive into the world of cybersecurity: explore what an AI attack is, gain valuable insights and stay informed about

Protecting against indirect prompt injection attacks in MCP

A type of Indirect Prompt Injection attack known as Tool Poisoning is a vulnerability where an attacker embeds

MCP Server Security: The Hidden AI Attack Surface

Our research demonstrates that both locally hosted and third-party MCP servers can be exploited to execute arbitrary

Attacking Artificial Intelligence: AI''s Security Vulnerability and What

An artificial intelligence attack (AI attack) is the purposeful manipulation of an AI system with the end goal of causing it to malfunction.

NIST Identifies Types of Cyberattacks That Manipulate Behavior of AI

AI systems can malfunction when exposed to untrustworthy data, and attackers are exploiting this issue. New guidance

MCP Security Issues Threatening AI Infrastructure | Docker

The horror story: The Tenable Website Attack demonstrates how tool poisoning, combined with localhost exploitation,

How to Recognize AI Attacks and Strategies for Securing Your AI

His research examines emerging threats across the AI attack surface and his work spans offensive and defensive AI

Top 5 AI Attack Surface Monitoring Platforms for CISOs in 2026

Compare the top 5 AI attack surface monitoring platforms for CISOs in 2026: CloudSEK AIVigil, Palo Alto Prisma

OpenAI says its AI went rogue and launched ''unprecedented'' cyber

OpenAI has revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of

Thousands of servers hacked in ongoing attack targeting Ray AI

Thousands of servers storing AI workloads and network credentials have been hacked in an ongoing attack campaign

Suspect in Molotov attack on Sam Altman''s home linked to AI Discord server

The 20-year-old suspect arrested after the Molotov cocktail attack on Sam Altman''s $27 million home participated in a

How AI Powers Modern Cyberattacks | 2026 Threat Guide

AI cyberattacks use artificial intelligence and machine learning to automate phishing, generate adaptive malware, create

AI-powered attacks: What CISOs need to know now

Learn how AI-powered attacks differ from traditional cybersecurity attacks and what business leaders must do to

Hackers Launch Over 91,000 Attacks on AI Systems Using Fake

A new investigation by GreyNoise reveals a massive wave of over 90,000 attacks targeting AI tools like Ollama and

AutoJack: How a single page can RCE the host running your AI agent

Microsoft Defender for Cloud AI Security Posture Management (AI-SPM) builds an AI bill of materials (AI BOM), scans

JadePuffer ransomware used AI agent to automate entire attack

According to cloud security company Sysdig, JadePuffer used an autonomous AI agent for reconnaissance on the

AI in the Middle: Turning Web-Based AI Services into C2 Proxies

Key Points Introduction AI is rapidly becoming embedded in day-to-day enterprise workflows, inside browsers,

An OpenAI test model escaped and broke into a real company''s

OpenAI says some of its experimental AI models left a test environment with no human direction and hacked their way