OpenAI’s advertising measurement system appears to use a cross-site cookie that can link activity on advertiser websites to a person’s ChatGPT account.…
Tag: AI Security
What AI Can, Cannot, and Should Not Do
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: What AI Can, Cannot, and Should Not Do
AI Models Cheat Benchmarks, CAIS Study Finds
A new benchmark from the Center for AI Safety reveals that leading AI models routinely take shortcuts and cheat when faced with challenging tasks.
RatHat Android Trojan Uses AI for Automation
The malware relies on AI for real-time device navigation and control, increasing adaptability and evasion.
Fastly gives enterprises real-time control over AI models and agents
Fastly has announced AI Runtime Control, AI Firewall, and new API Security capabilities designed to give organizations real-time visibility and control…
US and China Discuss Alerting Each Other to AI National Security Threats
Officials discussed setting up a mechanism for the two countries to notify each other of AI incidents which could threaten national security.
New Android Malware Uses AI to Steal Bank Logins and Reconstruct Your PIN
A newly identified Android banking Trojan called RatHat uses phone features for account theft. The malware can guide itself through an infected device,…
Google Confirms Gemini AI Breached Three Firms
Google is the latest AI giant to confirm that its models escaped a testing environment and hacked real companies.
OpenAI Codex sandbox escape, President proposes AI Force, Cyber Command suicides
Researchers escape OpenAI Codex sandbox to run commands on host AI Force proposed to monitor technology Congress eyes new support for Cyber Command after…
Huawei Expands AI Clustering Strategy
Huawei tests SuperPoD AI compute stack with UnifiedBus, near-packaged optics, brings forward launch of next-gen AI chips
BragJack Attack Hijacks AI Assistants in 5 Popular Browsers With Zero Clicks
Security researchers have revealed a zero-click attack technique known as BragJack, which could enable a malicious browser extension to hijack built-in AI…
AI compliance issues hit 2 in 5 large companies, and legacy workflows are a big factor
Forty percent of large companies had an AI-related compliance or governance issue in the past 12 months, according to 1,000 senior IT, operations, and…
Not you too Gemini? More AI hacking.
Gemini Breaches Real Companies, OpenAI SSO Hijacked, Browser AI Agents Exposed | Cybersecurity Today David Shipley covers multiple cybersecurity…
An AI Helped Researchers Break Into OpenAI
A three-person security research team quietly walked into OpenAI’s internal infrastructure last July, submitted a pull request inside the company’s…
AI Hallucinations Nearly Triggered a US-China Military Confrontation
An AI-generated intelligence report falsely identified weapons on a Chinese ship, nearly triggering a US military operation during the Iran war. According…
Court Filing Shows Microsoft Exec Called AI Training the “Largest Labor Theft in Human History”
The court documents made public this week show that Brent Hecht, Microsoft’s director of applied science, had cautioned that people could view large…
When Ransomware Targets AI Models: Defending the AI/ML Recovery Chain
By Crystal Morin Ransomware crews have always followed the money. For years, that meant targets like banks and hospitals organizations with high-value…
Autonomous AI Attacks: The Hugging Face Reality Check
For several years the forecast has been constant: AI lowers the skill barrier, AI writes novel malware, AI will soon run attacks end to end with minimal…
Plugin4Shell: The Zero-Click Flaw That Broke Every Prominent AI Coding Agent at Once
The security promise was simple. A plugin marketplace reviews a piece of code, locks it to a specific, verified version, and every AI coding agent that…
Google’s Gemini is the latest AI model to hack other companies
Google said Gemini had “acted appropriately” by ending each hack immediately.