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.
Google is testing a new image AI model called "Nano Banana 2 Flash," and it's going to be as good as the Gemini 3 Pro Nano Banana, but it'll be cheaper. [...]
If you're already subscribed to ChatGPT Plus, which costs $20, you can request OpenAI to cancel your subscription, and it may offer one month of free usage. [...]
IBM urged customers to patch a critical authentication bypass vulnerability in its API Connect enterprise platform that could allow attackers to access apps remotely. [...]
CISA ordered U.S. federal agencies to patch an actively exploited MongoDB vulnerability (MongoBleed) that can be exploited to steal credentials, API keys, and other sensitive data. [...]
OWASP's new Agentic AI Top 10 highlights real-world attacks already targeting autonomous AI systems, from goal hijacking to malicious MCP servers. Koi Security breaks down real-world incidents behind multiple categories, including two cases cited by OWASP, showing how agent tools and runtime behavior are being abused. [...]
OpenAI is rolling out an update to ChatGPT on mobile that finally allows you to select the Thinking time toggle, also called "juice" of the model. [...]