A researcher demonstrated a proof-of-concept attack chain that provided C2-style influence over ChatGPT's isolated sandbox during a session at Black Hat USA 2026.

Two former chief security officers of the Democratic National Committee explain that a strong security-first mindset requires executive support — and a dose of absurdity.

AI browsers from top vendors remain vulnerable to prompt injection attacks despite multiple security guardrails, according to new research.

Attackers can take control of agents through malicious instructions hidden in content supplied to AI browsers, and there's no simple fix for the threat.

Organized crime is convincingly scamming at scale, making billions thanks to AI-enabled voice cloning, deepfake real-time video overlays, LLM-driven persona management, and automated translation.

CSS was once just about design. Now researchers warn it's powerful enough to exfiltrate data from webmail — and some vendors aren't prepared.

Researchers are calling attention to the risks inherent in automated network device provisioning, using a world-leading device manufacturer as a case study.

Google has fixed the issues, which exploited a trust boundary between two AI agents with different privilege levels to trigger automation that could compromise the supply chain.

Unitel, Angola's dominant mobile operator, continues to recover from a cyberattack that caused outages the day of the government-owned telco's public offering.

The attacks use diverse social engineering lures and rotating payloads to deliver ScreenConnect for persistent remote access to compromised networks.

A Google Firebase misconfiguration lets users of tl;dv, an AI meeting tool, query any other users' meeting information and potentially join calls.

Newer social engineering techniques help attackers ignore entrenched security controls and limit the evidence they leave behind.

Over the weekend, the vendor discovered another vector of authentication bypass CVE-2026-18577 that gives attackers administrator access.

Researchers dug into the root of the problem with the goal of promoting industry collaboration on improved protective measures.

Last month's incidents in which the AI model breached real-world systems derived from over-permissioning, especially with Internet access.

Researchers intercepted and investigated the model, which was attempting to compromise more than 1,200 hosts for proxyjacking to launch further attacks.

Accountability without any real authority is driving CISO burnout, and organizations need to take notice.

A couple dozen changes to SBOM fields will make them more comprehensive, but some argue that the framework lacks real risk-management improvements.

The most valuable move any security team can make is building a certificate and key inventory.

Hundreds of thousands of California residents have already registered for the Delete Request and Opt-out Platform (DROP), which launches Aug. 1. Other states could follow if the process goes smoothly.

When a fraudulent transaction occurs, law enforcement agencies must work quickly to halt payments before cybercriminals cash out.

The organization behind Team USA's Olympic/Paralympic fencing teams has automated identity verification to handle growing membership, cutting manual review time while ensuring athletes compete in the correct categories.

A likely Iran-backed actor targeted more than 30 community water systems in Minnesota in a sobering reminder of rising threats to US critical infrastructure.

A myriad of software makes up the typical AI harness, and trust issues between the components can create concerning attack vectors.

In this edition of Reporters' Notebook, our journalists discuss the ins and outs of Anthropic's Claude Mythos rollout. How seriously should we take its risks? How big of a deal is it?

The organized crime groups have moved from goods to services and continue to traffic people from at least 80 countries, costing nations in the region at least $88 billion in 2025 alone.