31–40 of 43,219 articles
The Hacker News
Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons
An AI model can be given a hidden backdoor by editing fewer than 10 of its rarely used neurons, without retraining the model, Microsoft researchers have shown. When a chosen trigger appears, the model outputs an attacker's command, which an agent using that model would run with the agent's own permissions. The attacker must be able to change the model's weights. The team tested the method on
The Hacker News
Cisco BroadWorks and Openwave Flaws Actively Exploited Despite Available Patches
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) Tuesday added two security flaws impacting Cisco BroadWorks and Openwave Messaging Webtop Media Transcoder to its Known Exploited Vulnerabilities (KEV) catalog, citing evidence of active exploitation. Details of the vulnerabilities are below - CVE-2026-20320 (CVSS score: 7.5) - An improper restriction of XML external entity
The Register
OpenAI builds a kill switch for its research models
How much damage can a rogue agent do in 35 seconds? Asking cos that’s how long it might take to shut one down
Have I Been Pwned
СберСпасибо (SberSpasibo) - 3,288,711 breached accounts
In March 2023, data allegedly taken from СберСпасибо (SberSpasibo), the loyalty program of Russian bank Сбербанк (Sberbank), was published online. The data contained records relating to 48M users, including 3.3M unique email addresses alongside phone numbers and dates of birth. Data also included bank card numbers stored as unsalted SHA-1 hashes, plus loyalty program details such as membership dates and the redemption of bonus points for partner offers.
The Register
November Patch Tuesday boasts over 1,000 bugs but only one zero-day so far
Microsoft admins wail and gnash their teeth
Dark Reading
November Patch Tuesday: An Overflowing Cornucopia of CVEs
Microsoft serves up an actively exploited Outlook zero-day, and a wave of critical Exchange, SharePoint, Windows Search, and LDAP bugs that exhausted defenders need to prioritize fast.
Bleeping Computer
Railway breach leads to $740,000 in fraudulent AI charges
Cloud hosting provider Railway says hackers exploited vulnerabilities in its infrastructure to steal customer authentication secrets and generate approximately $740,000 in fraudulent AI usage, potentially exposing credentials for up to 100,000 workspaces. [...]
Krebs on Security
Microsoft Fixes Nearly 1,100 Security Vulnerabilities
Microsoft did another four-digit patch drop today, releasing updates to fix almost 1,100 security vulnerabilities in its Windows operating systems and supported software. This month's Patch Tuesday addresses 63 critical flaws -- including a zero-day in Microsoft Outlook -- and comes amid important security updates from other software makers, including Adobe, Apple, Google and Mozilla.
The Register
Ring robots ready to patrol paranoids’ pads
Amazon subsidiary unveils home security drone and business patrol bot to map your interior spaces keep you safe
Dark Reading
Artex: The AI Pen-Test Tool Hackers Turned Into a Weapon
Forks of the open source Artex framework, along with 45 similar pen-testing tools, remain capable of executing credential attacks and cloud breaches at machine speed across multiple industries.