A new prompt injection attack dubbed "BioShocking" could trick AI-powered browsers into treating real-world risky actions as part of a fictional scenario, causing them to ignore any safety guardrails. [...]
"Agentjacking" is the latest demonstration of how easily attackers can exploit an AI agent's inability to differentiate between content and instructions.
Microsoft announced today that it is accelerating its quantum-safe security roadmap, saying advances in quantum computing are bringing the need to replace today's encryption standards sooner than previously expected. [...]
A campaign active since last November has been targeting Python developers building Telegram bots with trojanized Pyrogram forks that allow attackers to read arbitrary files on compromised servers. [...]
Attackers don't need any special authentication to reach a target endpoint — they just need to know where it is.
Iniciativa vai atender pacientes menos graves nos horários de maior movimento, reduzindo o tempo de espera e aliviando a pressão sobre os serviços de urgência e emergência da capital gaúcha […] O post Secretaria Municipal de Saúde e Hospital Moinhos de Vento firmam parceria para …
As Forças de Autodefesa do Japão utilizaram, por quase um ano, drives USB infectados com um vírus atribuído a hackers chineses em computadores com acesso a informações classificadas, de acordo com uma investigação publicada pela agência Nikkei. A reportagem, baseada em documentos…
Telling an LLM that 2 + 2 = 5 is enough to make it follow forbidden instructions.
When Roche previewed the Axelios technology in February, a Jefferies analyst called the next-generation sequencing platform the “greatest credible competitive threat in years.”
A CLM, distribuidor brasileiro especializado em cibersegurança e infraestrutura para data centers, anunciou hoje parceria com a Claroty, para ampliar sua oferta de soluções de segurança para sistemas ciberfísicos (CPS) na América Latina. O acordo inclui tecnologias para proteção …
As AI reshapes cybersecurity workflows, John Paul Cunningham, CISO at SIlverfort, says the technology is creating opportunities rather than eliminating jobs — and there are more ways than ever to break into the essential field.
Separate but similar campaigns described by Microsoft and Trend Micro use malicious zip files to spread malware via social engineering and obsfucation, including blockchain abuse.
New Microsoft research shows how attackers can hijack AI agents that act on a user's behalf, using nothing more than a poisoned tool description to make the agent quietly hand over company data to an outsider. The trick is that the agent never breaks a rule. Every step looks rou…
A new two-stage malware family called RustDuck is hijacking home routers, IP cameras, Android boxes, and poorly secured servers, then stitching them into a network built to knock websites and online services offline. Researchers at QiAnXin's XLab have tracked it since February 2…
EvilTokens phishing hides takeover clues until browser execution leaving SOC teams needing deeper visibility to validate threats faster and reduce account risk.
By Ashley Blankette - Interconnected data continues to be the most valuable currency in healthcare administration. Attending AHIP ‘26 in Las Vegas, it became evident that the entire sector feels this pressure. The industry has reached a turning point where we can no longer afford…
A adoção de chatbots e assistentes com inteligência artificial nas empresas acelerou nos últimos meses. Equipes de atendimento, suporte interno, jurídico e financeiro passaram a contar com interfaces conversacionais alimentadas por LLMs para automatizar tarefas e responder pergun…
Learn how modern businesses can judge office software for ISO 27001 certification, GDPR-aligned data handling, encryption, and safer PDF workflows with clarity.
It is only a matter of time before a cyberattack is directly linked to the death of a patient, according to new research from the managed IT and security service provider Omega Systems. Last year, 52% of healthcare organizations expected a cyberattack to result in a patient fatal…
Threat actors are continuing to exploit a critical Langflow vulnerability as part of fresh attacks designed to deliver a Monero cryptocurrency miner. The activity has been found to weaponize CVE-2026-33017 (CVSS score: 9.3), an unauthenticated remote code execution (RCE) vulnera…
