New “Echo Chamber” attack bypasses advanced LLM safeguards by subtly manipulating conversational context, proving highly effective across leading AI models.
The post New AI Jailbreak Bypasses Guardrails With Ease appeared first on SecurityWeek.
Choosing a Clear Direction in the Face of Growing Cybersecurity Demands
In a rapidly changing AI environment, CISOs are worried about investing in the wrong solution or simply not investing because they can’t decide what the best option is.
The post Choosing a Clear Direction in the Face of Growing Cybersecurity Demands appeared first on SecurityWeek.
OpenAI to Help DoD With Cyber Defense Under New $200 Million Contract
OpenAI has been awarded a $200 million contract for AI capabilities to help the Defense Department address national security challenges.
The post OpenAI to Help DoD With Cyber Defense Under New $200 Million Contract appeared first on SecurityWeek.
Recent Langflow Vulnerability Exploited by Flodrix Botnet
A critical Langflow vulnerability tracked as CVE-2025-3248 has been exploited to ensnare devices in the Flodrix botnet.
The post Recent Langflow Vulnerability Exploited by Flodrix Botnet appeared first on SecurityWeek.
Red Teaming AI: The Build Vs Buy Debate
A strong AI deployment starts with asking the right questions, mapping your risks, and thinking like an adversary — before it’s too late.
The post Red Teaming AI: The Build Vs Buy Debate appeared first on SecurityWeek.
The AI Arms Race: Deepfake Generation vs. Detection
AI-generated voice deepfakes have crossed the uncanny valley, fueling a surge in fraud that outpaces traditional security measures. Detection technology is racing to keep up.
The post The AI Arms Race: Deepfake Generation vs. Detection appeared first on SecurityWeek.
Hirundo Raises $8 Million to Eliminate AI’s Bad Behavior
Hirundo tackles AI hallucinations and bias by making trained models “forget” poisoned, malicious, and confidential data.
The post Hirundo Raises $8 Million to Eliminate AI’s Bad Behavior appeared first on SecurityWeek.
‘EchoLeak’ AI Attack Enabled Theft of Sensitive Data via Microsoft 365 Copilot
Microsoft recently patched CVE-2025-32711, a vulnerability that could have been used for zero-click attacks to steal data from Copilot.
The post ‘EchoLeak’ AI Attack Enabled Theft of Sensitive Data via Microsoft 365 Copilot appeared first on SecurityWeek.
How Scammers Are Using AI to Steal College Financial Aid
Fake college enrollments have been surging as crime rings deploy “ghost students” — chatbots that join online classrooms and stay just long enough to collect a financial aid check.
The post How Scammers Are Using AI to Steal College Financial Aid appeared first on SecurityWeek.
The Root of AI Hallucinations: Physics Theory Digs Into the ‘Attention’ Flaw
Physicist Neil Johnson explores how fundamental laws of nature could explain why AI sometimes fails—and what to do about it.
The post The Root of AI Hallucinations: Physics Theory Digs Into the ‘Attention’ Flaw appeared first on SecurityWeek.
