AI data exfiltration Archives

PAM, access management, identity, credentials, AI chatbots botnets datadome Spam Bots and Fake Accounts

Hacker Uses Claude, ChatGPT AI Chatbots to Breach Mexican Government Systems

Jeffrey Burt | March 1, 2026 | AI data exfiltration, AI hackers, Anthropic Claude, Artificial Intelligence (AI), Data breach, Gambit Security, generative AI threats, Mexico, OpenAI ChatGPT

An unknown hacker used jailbreaking tactics against Anthropic's Claude and OpenAI's ChatGPT AI chatbots to exploit multiple weaknesses in Mexico's government networks and steal as much as 150GB of sensitive data, from ...

Security Boulevard

Exploiting Google Gemini to Abuse Calendar Invites Illustrates AI Threats

Jeffrey Burt | January 20, 2026 | AI cyber threats, AI data exfiltration, AI vulnerability, Google Calendar, Google Gemini security, LLM threats, miggo, prompt injection attacks, Runtime Application Security

Researchers with security firm Miggo used an indirect prompt injection technique to manipulate Google's Gemini AI assistant to access and leak private data in Google Calendar events, highlighting the challenges AI presents ...

Security Boulevard

Google Chrome Extension is Intercepting Millions of Users’ AI Chats

Jeffrey Burt | December 17, 2025 | AI chatbots, AI data exfiltration, Anthropic, browser extension threats, Data Brokers, Google Chrome, Google Gemini, Koi Security, malicious extensions, Microsoft Copilot, Microsoft Edge, OpenAI ChatGPT

A Chrome browser extension with 6 million users, as well as seven other Chrome and Edge extensions, for months have been silently collecting data from every AI chatbot conversion, packaging it, and ...

Security Boulevard

GenAI, multimodal ai, AI agents, CISO, AI, Malware, DataKrypto, Tumeryk,

Prompt Injection Can’t Be Fully Mitigated, NCSC Says Reduce Impact Instead

Teri Robinson | December 12, 2025 | AI agent security, AI Application Security, AI data exfiltration, AI observability, AI Risk Management, defense in depth for AI, ForcedLeak, GeminiJack vulnerability, Generative AI Security, least privilege for AI, llm security, llm vulnerabilities, NCSC guidance, OWASP top 10 for LLMs, prompt injection, prompt injection attacks, secure AI design

The NCSC warns prompt injection is fundamentally different from SQL injection. Organizations must shift from prevention to impact reduction and defense-in-depth for LLM security ...

Security Boulevard

AI data exfiltration

Senator Sanders Wants to Own AI Companies — and Hand America’s Adversaries the Keys

NIST’s Nine: The PQC Signature Race Moves to Round Three

The Quantum Arms Race: Why Washington Just Wrote a $2 Billion Check to Nine Companies

Beyond Moore’s Law: The Hyper-Acceleration of Autonomous AI Cyber Capabilities

The Exception Economy: When Security Teams Stop Protecting and Start Negotiating

GoPlus’s Latest Report Highlights How Blockchain Communities Are Leveraging Critical API Security Data To Mitigate Web3 Threats

C2A Security’s EVSec Risk Management and Automation Platform Gains Traction in Automotive Industry as Companies Seek to Efficiently Meet Regulatory Requirements

Zama Raises $73M in Series A Lead by Multicoin Capital and Protocol Labs to Commercialize Fully Homomorphic Encryption

RSM US Deploys Stellar Cyber Open XDR Platform to Secure Clients

ThreatHunter.ai Halts Hundreds of Attacks in the past 48 hours: Combating Ransomware and Nation-State Cyber Threats Head-On