Researchers Discover Major Security Gaps in LLM Guardrails
Palo Alto Networks’ Unit 42 has developed a successful attack to bypass safety guardrails in popular generative AI tools
General
20 articles
Cyber-Attacks on UK Firms Increase at Four Times Global Rate
Check Point data shows attack volumes are growing much faster in the UK than worldwide
OpenAI's Promptfoo Deal Plugs Agentic AI Testing Gap
OpenAI’s latest acquisition addresses a security need Jamieson O’Reilly, security advisor at OpenClaw, raised during an exclusive interview with Infosecurity
Iranian MOIS Actors & the Cyber Crime Connection
Key Points Iran-linked actors are increasingly engaging with the cyber crime ecosystem. Their activity suggests a growing reliance on criminal tools, service...
Only 24% Of organizations Test Identity Recovery Every Six Months
Only 24% of organizations test identity disaster recovery plans every 6 months, Quest Software said
FortiGate Edge Intrusions | Stolen Service Accounts Lead to Rogue Workstations and Deep AD Compromise
FortiGate SSO flaws allows attackers to steal configs, abuse AD creds, deploy RMM tools, and exfiltrate NTDS files.
Russian Hackers Target WhatsApp and Signal Accounts of Global Military and Government Officials
Dutch intelligence reveals Russian state hackers are trying to hijack the Signal and WhatsApp accounts of key targets
Announcing Prisma AIRS Availability in Singapore Region
Palo Alto Networks launches Prisma AIRS in Singapore. Get AI-native threat protection, data residency and cyber resilience.
Trump Administration Unveils New Cyber Strategy for America
US national cyber strategy focuses on stronger defenses, countering threats, fostering innovation
UK Launches New Crackdown Unit to Tackle Cyber-Fraud at the Source
New UK Online Crime Centre will combine expertise from a range of sources to takedown online channels cyber-scammers rely on
AI Security Startups Dominate New Cyber Innovation Awards
Over one in five winners of IT-Harvest’s 2026 Cyber 150 are AI security companies
Ghanaian Pleads Guilty to Role in $100m Romance Scam
Derrick Van Yeboah admitted he stole over $10m in romance scams as part of crime gang
How the National Cyber Strategy Secures Our Digital Way of Life
Palo Alto Networks applauds the new National Cyber Strategy. We detail our support for key aspects of its six pillars, to include AI security and quantum rea...
Zero‑Day Attacks on Enterprise Software Reach Record High, Google Warns
Almost a quarter of the zero days detected by Google in 2025 targeted security and networking appliances
What cybersecurity actually does for your business
The ability to continue operating safely in an unsafe environment where competitors cannot is a competitive advantage that is rarely measured or discussed
AI-Driven Insider Risk Now a “Critical Business Threat,” Report Warns
Malicious insiders are using misusing AI for nefarious gain, while employees cutting corners also creates risk, warns Mimecast
ContextCrush Flaw Exposes AI Development Tools to Attacks
Critical flaw "ContextCrush" in Context7 MCP Server could allow malicious instructions into AI tools
Cisco Issues Patches for 48 Vulnerabilities in Enterprise Networking Products
Two of the 48 Cisco vulnerabilities, affecting Secure Firewall Management Center, are maximum-severity flaws
How SMBs use threat research and MDR to build a defensive edge
We speak to Director of ESET Threat Research Jean-Ian Boutin about where solutions that blend advanced technology with human expertise provide the most pract...
On the Effectiveness of Mutational Grammar Fuzzing
Mutational grammar fuzzing is a fuzzing technique in which the fuzzer uses a predefined grammar that describes the structure of the samples. When a sample ge...