DeepSeek Compared to ChatGPT, Gemini in AI Jailbreak Test

DeepSeek’s susceptibility to jailbreaks has been compared by Cisco to other popular AI models, including from Meta, OpenAI and Google.

The post DeepSeek Compared to ChatGPT, Gemini in AI Jailbreak Test appeared first on SecurityWeek.

SecurityWeek – ​Read More

Taiwan Bans DeepSeek AI Over National Security Concerns, Citing Data Leakage Risks

Taiwan has become the latest country to ban government agencies from using Chinese startup DeepSeek’s Artificial Intelligence (AI) platform, citing security risks.
“Government agencies and critical infrastructure should not use DeepSeek, because it endangers national information security,” according to a statement released by Taiwan’s Ministry of Digital Affairs, per Radio Free Asia.
“DeepSeek

The Hacker News – ​Read More

Meet the Hired Guns Who Make Sure School Cyberattacks Stay Hidden

An investigation into more than 300 cyberattacks against US K–12 schools over the past five years shows how schools can withhold crucial details from students and parents whose data was stolen.

Security Latest – ​Read More

Microsoft Patches Critical Azure AI Face Service Vulnerability with CVSS 9.9 Score

Microsoft has released patches to address two Critical-rated security flaws impacting Azure AI Face Service and Microsoft Account that could allow a malicious actor to escalate their privileges under certain conditions.
The flaws are listed below –

CVE-2025-21396 (CVSS score: 7.5) – Microsoft Account Elevation of Privilege Vulnerability
CVE-2025-21415 (CVSS score: 9.9) – Azure AI Face Service

The Hacker News – ​Read More

Google Patches 47 Android Security Flaws, Including Actively Exploited CVE-2024-53104

Google has shipped patches to address 47 security flaws in its Android operating system, including one it said has come under active exploitation in the wild.
The vulnerability in question is CVE-2024-53104 (CVSS score: 7.8), which has been described as a case of privilege escalation in a kernel component known as the USB Video Class (UVC) driver.
Successful exploitation of the flaw could lead

The Hacker News – ​Read More

Microsoft SharePoint Connector Flaw Could’ve Enabled Credential Theft Across Power Platform

Cybersecurity researchers have disclosed details of a now-patched vulnerability impacting the Microsoft SharePoint connector on Power Platform that, if successfully exploited, could allow threat actors to harvest a user’s credentials and stage follow-on attacks.
This could manifest in the form of post-exploitation actions that allow the attacker to send requests to the SharePoint API on behalf

The Hacker News – ​Read More

Anthropic claims new AI security method blocks 95% of jailbreaks, invites red teamers to try

VentureBeat/Ideogram


The new Claude safeguards have already technically been broken but Anthropic says this was due to a glitch — try again.Read More

Security News | VentureBeat – ​Read More

Microsoft Will Remove the Free VPN That Comes With Windows Defender Soon

The feature will no longer be available starting Feb. 28. Microsoft wants to focus on “new areas that will better align to customer needs.”

Security | TechRepublic – ​Read More

Hackers Hide Malware in Fake DeepSeek PyPI Packages

Malicious DeepSeek packages on PyPI spread malware, stealing sensitive data like API keys. Learn how this attack targeted developers and how to protect yourself.

Hackread – Latest Cybersecurity, Tech, Crypto & Hacking News – ​Read More