Hacker Conversations: Joey Melo on Hacking AI 2026-05-05 at 16:30 By Kevin Townsend AI red team specialist details his methods for manipulating AI guardrails through jailbreaking and data poisoning, helping developers harden machine learning models. The post Hacker Conversations: Joey Melo on Hacking AI appeared first on SecurityWeek. This article is an excerpt from SecurityWeek […]
Hacker Conversations: Joey Melo on Hacking AI Read More »
Silent Drift: How LLMs Are Quietly Breaking Organizational Access Control 2026-03-30 at 17:30 By Kevin Townsend LLMs can write complex Rego and Cedar code in seconds, but a single missing condition or hallucinated attribute can quietly dismantle your organization’s least-privilege security model. The post Silent Drift: How LLMs Are Quietly Breaking Organizational Access Control appeared
Silent Drift: How LLMs Are Quietly Breaking Organizational Access Control Read More »
175,000 Exposed Ollama Hosts Could Enable LLM Abuse 2026-01-30 at 16:44 By Ionut Arghire Among them, 23,000 hosts were persistently responsible for the majority of activity observed over 293 days of scanning. The post 175,000 Exposed Ollama Hosts Could Enable LLM Abuse appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original
175,000 Exposed Ollama Hosts Could Enable LLM Abuse Read More »
LLMs Hijacked, Monetized in ‘Operation Bizarre Bazaar’ 2026-01-29 at 17:29 By Ionut Arghire An LLMjacking operation has been targeting exposed LLMs and MCPs at scale, for commercial monetization. The post LLMs Hijacked, Monetized in ‘Operation Bizarre Bazaar’ appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
LLMs Hijacked, Monetized in ‘Operation Bizarre Bazaar’ Read More »
LLMs in Attacker Crosshairs, Warns Threat Intel Firm 2026-01-12 at 14:19 By Ionut Arghire Threat actors are hunting for misconfigured proxy servers to gain access to APIs for various LLMs. The post LLMs in Attacker Crosshairs, Warns Threat Intel Firm appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
LLMs in Attacker Crosshairs, Warns Threat Intel Firm Read More »
‘Whisper Leak’ LLM Side-Channel Attack Infers User Prompt Topics 2025-11-11 at 14:10 By Ionut Arghire Attackers intercepting network traffic can determine the conversation topic with a chatbot despite end-to-end encrypted communication. The post ‘Whisper Leak’ LLM Side-Channel Attack Infers User Prompt Topics appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original
‘Whisper Leak’ LLM Side-Channel Attack Infers User Prompt Topics Read More »
Will AI-SPM Become the Standard Security Layer for Safe AI Adoption? 2025-10-08 at 19:31 By Etay Maor How security posture management for AI can protect against model poisoning, excessive agency, jailbreaking and other LLM risks. The post Will AI-SPM Become the Standard Security Layer for Safe AI Adoption? appeared first on SecurityWeek. This article is
Will AI-SPM Become the Standard Security Layer for Safe AI Adoption? Read More »
Beyond the Prompt: Building Trustworthy Agent Systems 2025-08-26 at 18:03 By Stu Sjouwerman Building secure AI agent systems requires a disciplined engineering approach focused on deliberate architecture and human oversight. The post Beyond the Prompt: Building Trustworthy Agent Systems appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
Beyond the Prompt: Building Trustworthy Agent Systems Read More »
Project Ire: Microsoft’s autonomous malware detection AI agent 2025-08-05 at 19:45 By Zeljka Zorz Microsoft is working on a AI agent whose main goal is autonomous malware detection and the prototype – dubbed Project Ire – is showing great potential, the company has announced on Tuesday. Tested on a dataset of known malicious and benign
Project Ire: Microsoft’s autonomous malware detection AI agent Read More »
From Ex Machina to Exfiltration: When AI Gets Too Curious 2025-07-29 at 14:00 By Danelle Au From prompt injection to emergent behavior, today’s curious AI models are quietly breaching trust boundaries. The post From Ex Machina to Exfiltration: When AI Gets Too Curious appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View
From Ex Machina to Exfiltration: When AI Gets Too Curious Read More »
Grok-4 Falls to a Jailbreak Two days After Its Release 2025-07-12 at 17:57 By Kevin Townsend The latest release of the xAI LLM, Grok-4, has already fallen to a sophisticated jailbreak. The post Grok-4 Falls to a Jailbreak Two days After Its Release appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View
Grok-4 Falls to a Jailbreak Two days After Its Release Read More »
What Can Businesses Do About Ethical Dilemmas Posed by AI? 2025-07-10 at 14:06 By Stu Sjouwerman AI-made decisions are in many ways shaping and governing human lives. Companies have a moral, social, and fiduciary duty to responsibly lead its take-up. The post What Can Businesses Do About Ethical Dilemmas Posed by AI? appeared first on
What Can Businesses Do About Ethical Dilemmas Posed by AI? Read More »
New AI Jailbreak Bypasses Guardrails With Ease 2025-06-23 at 17:02 By Kevin Townsend New “Echo Chamber” attack bypasses advanced LLM safeguards by subtly manipulating conversational context, proving highly effective across leading AI models. The post New AI Jailbreak Bypasses Guardrails With Ease appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original
New AI Jailbreak Bypasses Guardrails With Ease Read More »
What CISOs need to know about agentic AI 2025-06-13 at 08:34 By Anamarija Pogorelec GenAI has been the star of the show lately. Tools like ChatGPT impressed everyone with how well they can summarize, write, and respond. But something new is gaining ground: agentic AI. These systems don’t just answer questions. They make decisions, take
What CISOs need to know about agentic AI Read More »
Securing agentic AI systems before they go rogue 2025-06-10 at 08:24 By Help Net Security In this Help Net Security video, Eoin Wickens, Director of Threat Intelligence at HiddenLayer, explores the security risks posed by agentic AI. He breaks down how agentic AI functions, its potential to revolutionize business operations, and the vulnerabilities it introduces,
Securing agentic AI systems before they go rogue Read More »
Google’s ‘GPT-4 killer’ Gemini is out, here’s how you can try it 07/12/2023 at 07:02 By Cointelegraph by Martin Young Google has deployed its newest weapon in the AI arms race, a new artificial intelligence model that it claims is smarter and more powerful than OpenAI’s GPT-4. This article is an excerpt from Cointelegraph.com News
Google’s ‘GPT-4 killer’ Gemini is out, here’s how you can try it Read More »