Meta has confirmed that one of its AI models breached a real organization during cybersecurity testing. Thank you for being a Ghacks reader.
Tag: AI Security
ScienceLogic delivers secure AI deployment and smarter IT operations with Skylar AI 2.5
ScienceLogic has announced Skylar AI 2.5, expanding secure deployment options for organizations with stringent security, sovereignty, and compliance…
Deloitte strengthens AI governance to support trusted enterprise adoption
Deloitte has expanded AI Controls and Assurance services and solutions designed to help organizations confidently adopt, scale and govern AI across the…
AI agents exhibit deceptive behaviors
New research from Anthropic and collaborating AI laboratories has documented instances of large language models exhibiting deceptive behaviors during…
AI writes patches that don’t work, WordPress login takeover, Researchers hijack 36 million kids’ GPS trackers
AI Patch Development Fails, WordPress Login XSS Hits All Versions, and DEF CON’s Biggest Security Lessons David Shipley covers new research from…
Advertisers are trying to influence AI bots with secret ads
PLUS: Hiveminds are emerging to hack the planet, and open-weight models are the new new red scare
Mindgard Raises $30 Million to Protect AI Systems
The cybersecurity startup will use the fresh investment to scale its product, engineering, sales, and marketing teams.
OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models’ Reasoning
A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning…
‘The Worst I’ve Ever Seen’: Cargo Thefts Have Turned Violent in Pursuit of AI Hardware
Experts allege that two recent incidents in California show the extreme lengths that criminal organizations are willing to go to to steal servers and…
Nvidia Releases Open, Lightweight Nemotron AI Model
AI chip giant releases Nemotron 3.5 Lightning under open-weight licence, as it reportedly works on large-scale challenger with 1 trillion parameters
French Press Group Challenges Google Over AI Summaries
Press trade body calls on competition regulator to take action after Google introduces AI Overviews in France, amid EU probe
AI Token Prices Fall To Annual Low
Average token prices for AI inference fall to low for the year to date, amid release of low-cost Chinese models, increased US efficiency focus
AI Agent Hacks Gym To Book Spots For User
AI system unexpectedly hacks gym’s reservation system to book user into busy Pilates class, in latest reminder of agentic unpredictability
AI deployments are stretching enterprise security to its limits
CISOs and CTOs expect AI deployments to increase their organizations’ attack surface by an average of 14% over the next year. Nearly all lack visibility…
DefCon airplane Wi-Fi drama. GhostJacking leads to agent hijacks, AI agent hacks gym
DEF CON In-Flight Wi‑Fi Hack, 400 Microsoft Patches, and AI Agent ‘Ghostjacking’ Delta Air Lines is investigating a brief appearance of an unauthorized…
CrowdStrike Joins the Open Secure AI Alliance to Advance AI Safety and Security
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: CrowdStrike Joins the Open Secure AI Alliance to Advance AI Safety and Security
OpenAI, Anthropic, and Meta AI Breaches Shared the Same Testing Vendor
OpenAI, Anthropic, and Meta AI incidents reportedly shared one testing vendor, exposing third-party and containment risks in AI security evaluations.
Kimsuky Brings AI Closer to Its Malware and Phishing Operations
North Korean cyber-espionage group Kimsuky appears to be moving beyond occasional use of public AI services by assembling a local artificial intelligence…
The inconvenient truth about AI pentesting: someone has to check all the work
AI pentesting can flood teams with findings they cannot validate. The real challenge is managing “validation debt” as discovery scales. AI pentesting has…
Zenity Raises $125 Million Series C to Strengthen AI Agent Security and Governance
AI security and governance platform Zenity has announced a $125 million Series C funding round led by Norwest. The investment signals escalating…