Threat intelligence firm Hunt.io has documented a sophisticated Chinese-speaking cyberespionage campaign that integrated commercial AI models into live…
Tag: AI Security
KnowBe4 to Put AI Trust to the Test at Leeds Digital Festival
KnowBe4 is set to explore the growing challenge of determining what organisations can trust in the age of AI at an exclusive cybersecurity briefing during…
Nvidia Is Buying AI Platform Hugging Face for $13 Billion
The deal highlights Nvidia’s push to champion increasingly popular open-source AI models.
OpenAI Agents Hijack German Wiki in AI Breakout to Share Evasion and Bypass Tactics
Autonomous AI agents that identified themselves as OpenAI systems hijacked an obscure German-language wiki this spring and turned it into a public…
Catch Raises $5 Million for AI Executive Assistant With Guardrails
Catch promises the capabilities of a trusted executive assistant, with built-in controls governing what data and systems it can access.
Chinese Hackers Use AI Agents in Multi-Country Cyber Campaign
Hunt.io uncovered a Chinese-speaking campaign using AI agents to automate cyberattacks against Asian government, education and industrial targets. Threat…
AI Coding Agents Are Installing Unknown/Untrusted Code on Corporate Networks
We cannot forget that AI coding agents are not yet trustworthy : Researchers at a stealth startup in Israel scanned 6,214 live domains belonging to…
OpenAI Pledges $1bn to Bring its AI Cybersecurity Tools to Essential Services
OpenAI has committed to subsidizing access to Daybreak, helping defenders deploy its AI models in its existing cybersecurity infrastructure
Chinese-Speaking Hackers Use Claude, Qwen and DeepSeek AI Agents to Attack Government Systems
Chinese-speaking threat operators have been observed using Claude, Qwen and DeepSeek-powered AI agents as operational components in a second intrusion…
A five-part inventory for your AI agent credentials
In this Help Net Security video, Roy Katmor, co-founder and CEO of Orchid, explains why AI agents hold credentials that nobody reviews. Organizations…
LLMjacking Attack Abuses Leaked AWS Credentials to Hijack Amazon Bedrock AI Models
Threat actors are increasingly converting stolen cloud credentials into access to costly generative AI services, a technique known as LLMjacking.…
OpenAI commits $1B in AI credits to frontline cyber defenders
Daybreak program brings subsidized models, training, and support to under-resourced teams
Machine Speed is a lie: stop trying to fight AI with AI
Marketing departments are screaming that attackers are moving at “machine speed” and only AI-powered defenses can stop them. But cyberattacks have always…
Financial Stability Board Sounds the Alarm Over Frontier AI Risks
The Financial Stability Board has warned G20 banking leaders about the cyber risks of frontier AI
Introducing More Granular Controls for AI Bot Traffic
This post has no text preview — click the link below to read the original article. This article has been indexed from Blog Read the original article: Introducing More Granular Controls for AI Bot Traffic
Russia-Aligned UAC-0099 Plants Nuclear Weapon Prompt in Malware to Disrupt AI Analysis
Cybersecurity researchers have disclosed a new technique dubbed GuardBreaker that’s been put to use by a Russia-aligned threat actor known as UAC-0099…
Claude sessions hijacked, AI jolts global finance, agents get too many keys
Claude sessions get hijacked Anthropic is warning that common infostealer malware is stealing active Claude browser sessions, letting attackers get into…
Abliteration.ai is making a business out of removing AI guardrails
Abliteration.AI is making powerful AI models without guardrails easier to access, arguing that giving defenders the same tools as bad actors could…
Claude AI Faces Outage Impacting Mythos 5.1, Fable 5.1, and Opus 5
Anthropic’s Claude AI experienced a partial outage on September 3, 2026, disrupting requests across several Claude models and affecting developers,…
ASCII smuggling crosses over from AI prompt injection to phishing evasion
Invisible Unicode characters popularized for hiding instructions from AI models are now being used to obfuscate words before email filters parse them.