Help Net Security newsletters: Daily and weekly news, cybersecurity jobs, open source projects, breaking news – subscribe here!

Please turn on your JavaScript for this page to function normally.
AI vs human
A nearly undetectable LLM attack needs only a handful of poisoned samples

Prompt engineering has become a standard part of how large language models are deployed in production, and it introduces an attack surface most organizations have not yet …

Christa Dodoo
Your facilities run on fragile supply chains and nobody wants to admit it

In this Help Net Security interview, Christa Dodoo, Global Chair at IFMA, discusses how facility managers are managing supply chain risk in critical building systems. She …

AI agent
Who owns AI agent access? At most companies, nobody knows

AI agents are operating across production enterprise environments at scale, and the identity infrastructure managing their access has not kept up with their deployment. A …

Oracle Linux
Unbreakable Enterprise Kernel 8.2 ships with confidential computing support, XFS live repair

Many enterprise Linux deployments rely on hardware-level memory isolation to protect sensitive workloads from co-tenants and compromised hypervisors. Oracle’s …

Prison
Botnet operator behind $14 million in ransomware extortion payments gets 24 months behind bars

A Russian national has been sentenced to 24 months in prison after admitting he managed a botnet used to launch ransomware attacks against dozens of U.S. companies. The judge …

dark web
Gemini picks up criminal activity buried in dark web noise

To help teams make faster and more accurate decisions on emerging threats, Google has introduced a dark web intelligence capability in Google Threat Intelligence. Powered by …

supply chain
LiteLLM PyPI packages compromised in expanding TeamPCP supply chain attacks

A slew of supply chain attacks against popular open source tools and packages appears to have been orchestrated by TeamPCP, a cybercriminal group that rose to prominence in …

Microsoft Entra ID
Microsoft hands Entra ID users new option for MFA

Organizations rely on MFA to enforce identity checks before granting access to systems and services. Microsoft has made external MFA generally available in Microsoft Entra ID, …

Anthropic
Anthropic trims action approval loop, lets Claude Code make the call

Auto mode is a new permissions feature in the Claude Code system that allows the AI to make approval decisions on a user’s behalf while safeguards review actions before …

Google
Google’s TurboQuant cuts AI memory use without losing accuracy

Large language models carry a persistent scaling problem. As context windows grow, the memory required to store key-value (KV) caches expands proportionally, consuming GPU …

AI
Training an AI agent to attack LLM applications like a real adversary

Most enterprise software development teams now ship AI-powered applications faster than traditional penetration testing can keep up with. A security team with 500 applications …

breach
You don’t have to choose between BAS or automated pentesting, you shouldn’t

There’s a debate making the rounds in security circles that sounds reasonable on the surface but falls apart under operational scrutiny: Which is better, breach and attack …

Don't miss

Cybersecurity news
Daily newsletter sent Monday-Friday
Weekly newsletter sent on Mondays
Editor's choice newsletter sent twice a month
Periodical newsletter released when there is breaking news
Weekly newsletter listing new cybersecurity job positions
Monthly newsletter focusing on open source cybersecurity tools