Hidden Prompts Trick AI Into False Email Summaries
With some simple HTML that's invisible to users, attackers can manipulate AI-powered email summarizers into producing malicious information.
Security news
Latest security news
Read recent coverage from BleepingComputer, Dark Reading, SecurityWeek, and The Hacker News, plus original research from SecurityAlert.
From security publishers
Dark Reading
Browse collected headlines and short excerpts from this publisher. Open the original article for the complete reporting.
114 publisher articles
SecurityAlert keeps the publisher's headline, a short feed excerpt, the publication date when available, and detected security signals. The linked article remains the source.
Finding Nemo(Claw): Networking Issue Allows for LLM Poisoning in OpenClaw
Attackers can exploit a security bug in Nvidia's tool to gain unauthenticated access to the local model server through the Ollama API, paving the way for persistent AI agent corruption.
Is Cyber Facing an Affordability Crisis?
As breach costs reach record highs and defense spending nears $240 billion, small businesses are dangerously exposed, threatening supply chain security.
Exploited Zimbra Flaw Highlights Shrinking Window to Patch
CISA issued a three-day deadline for agencies to patch a Zimbra security vulnerability, CVE-2026-73570, which allows full takeover of a user's communications.
Foul Language: WordlistLoader Disguises Malware as Ordinary Text
ClickFix-style threat campaigns are using a new trick to evade detection and deliver Amatera, an increasingly prevalent infostealer.
Tricky 'SynkLoader' Multitool May Herald Ransomware
An advanced, multilingual malware family brings back a trick from yesteryear - screen hijacking - for effective password theft, along with a slew of novel features.
ToxicPanda Banking Trojan Matures Into Enterprise Threat
The latest version of the Android malware has new features that expand its global reach and put more than users' financial applications at risk.
The Vulnerability Gap: Why Discovery Is Outrunning Repair
The combination of AI both discovering more vulnerabilities at a faster pace and the tightening regulatory environment is making this an all-hands-on-deck moment for the cybersecurity community.
How an Emerging Industrial Protocol Family Could Put OT at Risk
New research shows how attacks against some unprotected TSN protocols could allow attackers to disrupt or manipulate physical processes.
OWASP Flags Top AI Skill Risks in New Security Blueprint
The Open Worldwide Application Security Project has a brand-new top 10 security list tailored for the modern era, and it debuts a Universal Skill Format to add consistency and security to the AI add-ons.
Calling on Cyber Pros to Help Defend City Hall
Government agencies with smaller budgets need support - and here's how you can help.
Calling on Cyber Pros to Help Defend City Hall
Government agencies with smaller budgets need support - and here's how you can help.
OpenAI Adds Controls That Should've Been There Already
The new AI security controls follow the Hugging Face incident last month, though experts say many of these additions should have been in place prior to the frontier models escaping.
Hardware Makers Implement Post-Quantum Cryptography as Security Threats Near
The coming threat of super-powerful computers capable of cracking today's algorithms requires upgrading encryption now. Tech companies have begun building defenses.
New CUSTODY Framework Constrains AI Agents Inside the Network
Enterprise cybersecurity expert Jake Williams joins the Dark Reading News Desk to explain why he decided to release his new agentic AI framework in the wake of the OpenAI attacks on Hugging Face.
What We Missed: Delta Flight Disrupted With Wi-Fi Hack
In this video, Dark Reading editors discuss some of the news they didn't get a chance to cover, including some scary airplane security risks and the US government's newest "hack back" strategy.
N-able Bug Exposes Password Vault Master Keys
The popular "Passportal" password manager, favored by MSPs and SMBs, remains risky even after its patch, thanks to its cloud-based design. Should these products stay away from the cloud entirely?
Money and Mindset: The Two Biggest Roadblocks to Cyber Policing
Law enforcement training is falling behind the volume and rapid evolution of cybercrimes. Officers really only need to learn the basics, but lack of focus and budget hinder progress.
Before you act
Check the details before you act.
An article can point you toward something worth investigating, but it cannot tell you whether a product is installed in your environment or whether an attack affects your organization.
Read the linked article, check any named CVE or vendor advisory, and use Pulse to compare the story with the technologies and threats you monitor.