darkreading

Escalating threats are forcing boards to prioritize security, but communication gaps persist. Boards and security teams each say they need more support to bridge the divide.

The hacking of Hugging Face by a rogue OpenAI agent is significant, but unsurprising — and preventing the next AI model escape will be difficult, at best.

A porous API endpoint exposes, names, email addresses, country, and site status, all of which can be easily gleaned by anyone with a browser.

Microsoft addresses a public-by-default configuration and chain of code flaws in Azure Automation that could have let attackers seize another tenant's identity and access others' data, credentials, and cloud workloads.

The AI security layer and guardrails for many AI products don't evenly protect against jailbreaking and unsafe actions in every single language.

A state-sponsored threat group, dubbed "Laundry Bear," sends "half-click" phishing emails that require a victim only to open or preview the message.

Core issues that slowed down adoption of secure data vaults are being resolved by technology, but artificial intelligence poses new ones. Experts have some answers.

Portuguese businesses operate in the same native language as Brazilian hackers, making those businesses easy targets.

A cyberattack on a food and logistics firm disrupts the supply of frozen food to thousands of clients, including major franchises like Kentucky Fried Chicken.

Ahead of Black Hat USA, researchers find exploitable flaws in how Microsoft handles passkeys that could allow attackers to impersonate privileged users.

Sandworm_Mode is an early example of malware that exploits trusted AI tools and workflows to make malicious activity virtually indistinguishable from normal activity.

A malicious application delivers four-stage Android spyware via phony Google Play sites, exploiting civilian fear during Iranian missile strikes.

Advanced LLMs escaped their sandboxes while attempting to achieve a non-malicious benchmark test objective.

European and US banks inadvertently transmitted customer data to ad platforms via tracking pixels, raising serious compliance, security, and privacy concerns.

Researchers pointed to fragmentation of the ransomware ecosystem, the emergence of new attackers, and expansion of attacks on less defended organizations.

The latest large language models have high false-positive rates and fail to take into account the context of scans, leading to more work for AppSec professionals.

A Russian-speaking actor, "Trim," dismantled publicly available frontier models and integrated them with offensive security tools.

AI-generated code introduces 15 vulnerabilities on average per codebase, but the actual risk depends on framework pairing more than the model used.

Barely three days after disclosure, attackers are widely chaining together CVE-2026-60137 and CVE-2026-63030 to lob exploit attempts against one of the largest attack surfaces on the Internet.