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.
Securing AI within your organization starts with understanding how AI differs from traditional business tools. Google's Secure AI Framework provides a model for what to do next.
From AI to just plain aaaiiiee! Microsoft introduced its Bing Chat AI search assistant in February and a month later began serving ads alongside it to help cover costs.…
Malwarebytes said the goal of these tactics is to lure victims into downloading malicious software
Malicious ads served inside Microsoft Bing's artificial intelligence (AI) chatbot are being used to distribute malware when searching for popular tools
Malicious advertisements are now being injected into Microsoft's AI-powered Bing Chat responses, promoting fake download sites that distribute malware. [...]
Artificial intelligence and machine learning aren't yet delivering on their cybersecurity promises. How can we close the gaps?
The URLs needed to share chat histories have been indexed. Of course Google's Bard chatbot is currently being re-educated to better understand privacy.…
Microsoft's new AI image generation Paint tool powered by OpenAI's DALL-E text-to-image model is now rolling out to Windows Insiders in Dev and Canary channels. [...]
Microsoft has released the Windows 11 22H2 'Moment 4' update, bringing 150 new features, including new AI-powered versions of Paint, ClipChamp, Snipping tool, and the new Microsoft Copilot. [...]
Generative AI is a double-edged sword, if there ever was one. There is broad agreement that tools like ChatGPT are unleashing waves of productivity across the business, from IT, to customer experience, to engineering. That's on the one hand. On the other end of this fencing match: risk. From IP leakage and data privacy risks to the empowering of cybercriminals with AI tools, generative AI