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...
Help Net Security
19 articles
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...
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 ...
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’...
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.
Vorlon adds forensics and response to secure AI agents
Vorlon has unveiled AI Agent Flight Recorder and AI Agent Action Center, adding forensics and coordinated response to secure enterprise agentic ecosystems an...
DigiCert Document Trust Manager enhancements improve document security and compliance
DigiCert has announced enhancements to its Document Trust Manager solution to help organisations combat rising document fraud, simplify global compliance, an...
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 Intellig...
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 t...
Akamai Brand Guardian detects and removes AI-driven brand impersonation
Akamai has introduced Akamai Brand Guardian, an evolution of Brand Protector that uses AI to identify and manage brand impersonation at scale. Scammers are e...
Njordium AI blocks fake invoices and fraudulent payments
Njordium Cyber Group has launched its new AI Fraud Detection Module, a self-learning AI engine integrated into the recently released Vendor Management System...
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 M...
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 act...
Codenotary introduces AgentX for autonomous Linux infrastructure security
Codenotary has announced the availability of AgentX, an autonomous platform designed to manage, secure, and protect large-scale Linux infrastructure in the c...
Spur Intelligence delivers deeper visibility into anonymized infrastructure
Spur Intelligence has announced new enhancements to its IP intelligence platform, designed to give security and fraud teams deeper visibility into anonymized...
Tenable Hexa AI automates exposure management and security workflows
Tenable has revealed Tenable Hexa AI, the agentic AI engine of the Tenable One Exposure Management Platform that automates security workflows and transforms ...
Barracuda strengthens cyber resilience with BarracudaONE platform updates
Barracuda Networks has announced advancements to the BarracudaONE cybersecurity platform and Barracuda Partner Success Program. The latest innovations streng...
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,...
HPE enhances security to support AI and distributed enterprise environments
HPE has unveiled new security innovations designed to help organizations scale distributed operations, reduce cyber risk, and maintain consistent governance ...