The Game-Changing Launch That Should Make Security Teams Nervous OpenAI just launched “Developer Mode” for ChatGPT, giving Plus and Pro subscribers full read-and-write access to external tools via the Model Context Protocol (MCP). The company itself describes the feature as “powerful…
AI Misuse in the Wild: Inside Anthropic’s August Threat Report
Anthropic released its August 2025 threat intelligence report, adding to a growing body of evidence that artificial intelligence is now deeply embedded in criminal operations. Security researchers have long anticipated this shift, but the specificity of the examples in this report makes…
Key Takeaways from IBM’s 2025 Cost of a Data Breach Report
For 20 years, IBM’s Cost of a Data Breach Report has been one of the industry’s most trusted sources on the financial and operational impact of security incidents. Each edition provides a rare combination of breadth, spanning hundreds of breaches across industries and geographies,…
Why AI Security is Mission-Critical for AppSec Teams
How Application Security can stay ahead in the age of AI-powered development The rise of Generative AI (Gen AI) is transforming how software is built, tested, and deployed—and Application Security (AppSec) teams are on the front lines of this shift. As…
AI Security Series: What It Really Takes to Secure Gen AI
This is Acuvity’s AI Security Series which offers a comprehensive exploration of securing AI systems, particularly focusing on Large Language Models (LLMs) and agentic applications. Each installment delves into critical components of AI security, providing insights and strategies for enterprises to protect their…
AI Security Series 5 – Model Training
As enterprises increasingly adopt Large Language Models (LLMs), some choose to pre-train or fine tune models. This blog describes problems that one needs to be aware of when they are indeed training models. In this part of the series we will…
AI Security Series 4 – Model Usage
At the heart of any AI application or agentic system are LLMs. Your developers and vendors are using multiple LLMs to achieve the right balance of quality and cost to deliver the workflow automations and agentic systems. In this section we…
AI Security Series 3 – Datastores
Modern AI applications—especially those involving conversational agents, retrieval-augmented generation (RAG), and enterprise copilots—depend heavily on a variety of datastores to supply, retrieve, and manage knowledge. Below is an outline of various data subsystems that are used in AI applications and agents. Together, these datastores…
AI Security Series 2 – Gen AI Application Security Pillars
As enterprises rapidly integrate AI systems into core workflows, the need to adopt a security-first mindset becomes imperative. These systems, especially those built on architectures like Retrieval-Augmented Generation (RAG) and agentic execution patterns, introduce novel security concerns far beyond traditional software…
AI Security Series 1 – Applications and Agents
Introduction The rapid advancement of AI technologies—particularly large language models (LLMs) and agentic systems—has transformed the way modern applications are built and operated. From personalized customer support chatbots to autonomous agents that perform multi-step reasoning and execute tasks on behalf of…