Prompt injection tags along as GenAI enters daily government use
Routine use of GenAI has moved into daily operations in state and territorial government environments, placing new security risks within common workflows. A Center for …
Google study finds LLMs are embedded at every stage of abuse detection
Online platforms are running large language models at every stage of LLM content moderation, from generating training data to auditing their own systems for bias. Researchers …
Financial groups lay out a plan to fight AI identity attacks
Generative AI tools have brought the cost of deepfake production low enough that criminals and state-sponsored actors now use them routinely against financial institutions. A …
Breaking out: Can AI agents escape their sandboxes?
Container sandboxes are part of routine AI agent testing and deployment. Agents use them to run code, edit files, and interact with system resources without direct access to …
AI SOC vendors are selling a future that production deployments haven’t reached yet
Vendors selling AI-powered security operations platforms have built their pitches around a consistent set of promises: autonomous threat investigation, dramatic reductions in …
A nearly undetectable LLM attack needs only a handful of poisoned samples
Prompt engineering has become a standard part of how large language models are deployed in production, and it introduces an attack surface most organizations have not yet …
Google’s TurboQuant cuts AI memory use without losing accuracy
Large language models carry a persistent scaling problem. As context windows grow, the memory required to store key-value (KV) caches expands proportionally, consuming GPU …
Llamafile, Mozilla’s portable LLM runner, gets GPU support and a rebuilt core
Running a large language model on a single machine without cloud access or a container runtime remains a priority for practitioners working in air-gapped or …
AI got it wrong with high confidence. Now what?
In this Help Net Security interview, Christian Debes, Head of Data Analytics & AI at SPRYFOX, talks about the growing gap between what AI models do and what their …
Engineering trust: A security blueprint for autonomous AI agents
AI agents have evolved from just chatbots, answering questions to executing actions using various integrated tools, often autonomously, and as such the traditional security …
LLMs change their answers based on who’s asking
AI chatbots may deliver unequal answers depending on who is asking the question. A new study from the MIT Center for Constructive Communication finds that LLMs provide less …
Waiting for AI superintelligence? Don’t hold your breath
AI’s impact on systems, security, and decision-making is already permanent. Superintelligence, often referred to as artificial superintelligence (ASI), describes a …
Featured news
Resources
Don't miss
- A stranger has been reading Salesforce and ServiceNow portals worldwide for 17 months
- Microsoft patches 400+ vulnerabilities, one zero-day under attack (CVE-2026-68820)
- Post-quantum migration gets harder when every user holds a key
- PentestGPT: Open-source automated penetration testing agentic framework
- 338 million attack simulations reveal the state of enterprise defense