Explore the intersection of AI and cybersecurity. Stay informed on AI-driven security trends, tools, and threats in the ever-evolving digital landscape.
Search across headline titles and summaries.
Background for this topic.
Artificial intelligence (AI) describes computer systems that perform tasks such as recognizing patterns, making predictions, understanding language, or generating content. In security reporting, the term commonly includes machine-learning models used for detection and analysis, as well as generative AI applications that produce text, code, images, or other outputs.
AI can help analyze security telemetry, prioritize vulnerabilities, and support investigations, but its outputs can be wrong or manipulated. Important attack surfaces include prompt injection that steers an application into unintended actions, sensitive data being exposed through prompts or model outputs, and excessive permissions granted to AI systems that use external tools. Models can also be degraded by poisoned training data or evaded with carefully crafted inputs. Practitioners should protect training and operational data, limit model access and tool permissions, test for adversarial behavior, and require appropriate human validation before high-impact decisions.
The vulnerabilities exist in the widely used TorchServe framework, used by Amazon, Google, Walmart, and many other heavy hitters.
By reframing the narrative of the filter, the large-language model chatbot was more willing to solve the visual puzzle and override its programming.
A set of critical vulnerabilities dubbed 'ShellTorch' in the open-source TorchServe AI model-serving tool impact tens of thousands of internet-exposed servers, some of which belong to large organizations. [...]
NSA Director Gen. Nakasone made the announcement during a discussion in Washington last Thursday
APIs, also known as application programming interfaces, serve as the backbone of modern software applications, enabling seamless communication and data exchange between different systems and platforms. They provide developers with an interface to interact with external services, allowing them to integrate various functionalities into their own applications
The startup claims its private AI software is working on making decisions based on generalizing from examples.
Red Teams can help organizations better understand vulnerabilities and secure critical AI deployments.
Email security provider Egress found that AI detectors were unable to identify if a phishing email came from an AI chatbot