chatgpt
-
The WARP Vulnerability: How Adversaries Are Poisoning the Information Pipeline for AI Research Agents
A significant security flaw has emerged in the way next-generation “deep-research” AI agents navigate the web. Rather than attacking the…
Read More » -
Exploiting Trust: How Malvertisers Leveraged GitLab and Claude.ai for In-Memory RAT Deployment
A highly sophisticated malvertising and social engineering campaign has recently emerged, showcasing a tactical pivot from weaponized GitLab Pages to…
Read More » -
Egress Over Ingress: How OpenAI’s Lockdown Mode Mitigates Data Exfiltration
OpenAI has officially introduced Lockdown Mode, a strategic security hardening feature for ChatGPT designed to mitigate the critical risk of…
Read More » -
Destructive Cyber Campaign “Ababil of Minab” Targets Critical IT and Backup Infrastructure
A sophisticated and highly destructive cyber campaign is currently sweeping through organizations in the Middle East and beyond. Unlike traditional…
Read More » -
Deepfake Deception: Inside BlueNoroff’s AI-Driven Fileless Malware Campaign
In a sophisticated evolution of state-sponsored cyber espionage, the North Korean threat actor BlueNoroff (an affiliate of the Lazarus Group)…
Read More » -
Securing the Frontier: OpenAI’s GPT-5.5 Bio Bug Bounty Program Aims to Improve AI Safety and Performance
As large language models (LLMs) transition from general-purpose assistants to highly sophisticated cognitive engines, the surface area for potential misuse…
Read More » -
The Evolution of Deception: Unmasking North Korean ‘Laptop Farms’ and Remote Work Infiltration
North Korean threat actors are refining a high-stakes social engineering playbook, leveraging the global shift toward remote work to bypass…
Read More » -
OpenAI Launches GPT-5.4-Cyber to Bolster Cyber Defenses
OpenAI has introduced GPT-5.4-Cyber, a purpose-built variant of its flagship GPT-5.4 model, fine-tuned specifically for advanced defensive cybersecurity workflows. The…
Read More » -
AI-Powered Cyberattack on Mexican Government Exposes Hundreds of Millions of Records
In a groundbreaking technical report released by Gambit Security researcher Eyal Sela, new details have emerged about a massive cyberattack…
Read More » -
One Line, Eleven Models: The Sockpuppeting Technique That Defeats AI Safeguards
A newly discovered jailbreak technique called “sockpuppeting” can force 11 leading AI models—including ChatGPT, Claude and Gemini—to bypass their safety…
Read More » -
Trojanized PyPI AI Proxy Steals Claude Prompt, Exfiltrates Data
A malicious PyPI package, hermes-px, masquerades as a “Secure AI Inference Proxy” while secretly stealing user prompts and abusing a…
Read More » -
Malicious Chrome Extension “ChatGPT Ad Blocker” Targets Users, Steals Conversations
Security researchers have exposed a malicious Google Chrome extension dubbed “ChatGPT Ad Blocker,” which stealthily pilfers private AI dialogues. The…
Read More » -
ChatGPT Vulnerability Enabled Silent Leakage of Prompts and Sensitive Information
Artificial intelligence assistants increasinglyhandle our most sensitive data, operating under the assumption that enclosed environments keep this information secure. However,…
Read More » -
Malicious Browser Extensions Hijack Users’ AI Chats in New “Prompt Poaching” Attack
A new wave of malicious browser extensions is quietly harvesting sensitive user interactions with AI tools, now widely recognized as…
Read More » -
AI-Driven Phishing Attacks Bypass Email Filters, Land in Inboxes
AI-generated phishing is rapidly reshaping email risk, with more attacks slipping past filters and landing directly in users’ inboxes, even…
Read More » -
OpenAI’s Codex Security Built to Automate Vulnerability Discovery and Remediation
OpenAI has officially introduced Codex Security, an advanced application security agent designed to automate vulnerability discovery and remediation. Formerly known…
Read More »