Cisco study finds major frontier models susceptible to multi-turn prompt injection attacks
Single-turn attack success rates are not a reliable benchmark for model safety, Cisco concludes.
General
20 articles
MacGregor Voyage Data Recorder (VDR) G4e
View CSAF Summary Successful exploitation of these vulnerabilities could result in an attacker gaining administrator access to the device. The following vers...
New AI Usage Report: Enterprise AI Risk Is Heavily Concentrated Among a Small Group of AI "Power users"
State of AI Usage Report 2026 (full report here) by LayerX Security reveals the extent of the enterprise AI visibility gap and why most organizations still d...
Raising the Cybersecurity Stakes: Ante up for the Agentic Era
CISOs are now facing machine-speed attacks and asking, “How do I agent?” The industry must provide remediation at scale.
OWASP launches FinBot to help developers secure AI agents
OWASP’s FinBot gives developers hands-on training to secure AI agents.
A Fake UK Visa Site Left 100,000 Passports Wide Open
A third-party UK visa site exposed passports and selfies on a public AWS server. It’s not official GOV.
Top 10 Best Mobile Application Security Testing (MAST) Tools in 2026
As mobile usage continues to dominate the digital landscape, securing mobile applications has never been more critical. The year 2026 brings new challenges t...
The AI governance imperative you can’t afford to ignore
CIOs rushing to roll out AI agents without real visibility into their decision-making processes are flirting with disaster. According to AI experts, deployin...
Infosecurity Europe: Cybersecurity Staff Prefer CISOs With Real Attack Response Experience, Study Reveals
ISC2 survey of cybersecurity professionals suggests that staff want their information security leaders to have experienced reacting to a significant cyber in...
Microsoft’s new cloud PCs place AI agents under enterprise controls
Microsoft’s Windows 365 for Agents, a cloud PC platform for agentic workloads, runs AI agents in secure environments. Organizations can direct agents with na...
Google Unveils AI Threat Defense Platform to Fight AI-Powered Cyberattacks
New AI Threat Defense platform combines capabilities from Mandiant, Wiz and Gemini to help customers fight AI with AI. The post Google Unveils AI Threat Defe...
GCHQ Chief Urges Action as AI Reshapes Cyber Threats
GCHQ director urges urgent business cyber action as AI and quantum reshape the threat
Sextortionist sentenced to 33 years for targeting 145 children
A Canadian man was sentenced to 33 years in prison after pleading guilty to targeting more than 145 children across the United States, some as young as 6 yea...
What the industrialization of exploitation means for defenders
For decades, cybersecurity was a battle of skill. Elite attackers versus elite defenders.
19.6 Billion Files Are Sitting Open on the Internet. No Password Required
19.6 Billion files are exposed in misconfigured cloud buckets, including 685K credential files and nearly 1M database dumps.
Ketch brings multi-agent AI orchestration to enterprise privacy programs
Ketch has unveiled its vision for agentic privacy with the Ketch Agent Network, a multi-agent orchestration layer for enterprise privacy programs. The platfo...
Motorola App Allegedly Hijacks Amazon App Activity to Insert Affiliate Referral Codes
Motorola is facing scrutiny after researchers and users discovered that its preinstalled Smart Feed app was silently hijacking launches of the Amazon Shoppin...
Checksum introduces Continuous Quality Agent for automated test generation and healing
Checksum has launched its Continuous Quality Agent, an autonomous system that runs nightly against deployed applications and automatically heals broken tests...
Police arrest suspect in Ajax football club hack that exposed 300,000 fan records
The Dutch National Police arrested a man suspected of hacking into the computer systems of AFC Ajax, a football club from Amsterdam. “On the morning of Tuesd...
Pirates in the crosshairs: how one cybercrime gang has been infecting book, movie, and TV show fans for years
Our experts continue to track attacks targeting consumers of pirated content, both books and movies. 2026 saw the discovery of new target sites with tens of ...