No signal on this page matches that topic.
Gartner named Straiker a Pioneer in its Emerging Market Quadrant for AI Application Security. Explore the quadrant…
Self-generated prompt injections in compaction summaries In Our framework for reporting model misalignment OpenAI…
The past few weeks have “felt very strange” for Juan Andres Guerrero-Saade. Like many, he is trying to sort through the…
OpenAI has presented new examples of what they call "AI model misalignment" from the past six months, including unauthorized file uploads, following self-generated instructions, hiding mistakes, and…
In response to a new European Union law, AI platforms are implementing new schemes for watermarking the content they…
Welcome to this week’s edition of the Threat Source newsletter. There’s been a lot of talk recently about slowing down…
AI has already made fundamental changes to the operating environment for cybersecurity. Cyberattackers are testing more…
Every benchmark tells a story. The most valuable ones tell us where to improve next. For five consecutive quarters…
TLDR: CiliumHound is a BloodHound OpenGraph extension for auditing Cilium network policies. It ingests a folder of JSON or YAML policies and creates a searchable, Kubernetes namespace-scoped graph…
The defining development of the period came not from attackers but from the AI labs themselves, whose models broke out…
Analyzing model input and output logs in an AI-native detection pipeline to understand and uncover malicious AI agent…
AI tools are already in your practice. The question is whether you know about it and whether they are HIPAA compliant…
Improper neutralization of special elements used in a command ('command injection') in Microsoft Copilot allows an…
Incorrect authorization in Azure Machine Learning allows an unauthorized attacker to disclose information over a network.
Improper neutralization of special elements used in a command ('command injection') in M365 Copilot allows an…
Improper neutralization of special elements used in a command ('command injection') in Microsoft 365 Copilot's Business…
Missing authentication for critical function in Azure AI Foundry allows an unauthorized attacker to elevate privileges…
Server-side request forgery (ssrf) in Azure AI Foundry allows an unauthorized attacker to elevate privileges over a…
Vibe coding is democratizing software development, but it is also creating a massive shadow AI attack surface. Security teams cannot rely on bans to address this risk, so they need to build "paved…
Welcome back to PWNED, the weekly column where we learn important life lessons about how we let cybercrims access our…