Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

In this video from Black Hat 2025, A10 Networks security expert Jamison Utter explains the importance of a unified, "one mind" approach to API security. He argues against the traditional, "stitched-together" method of using separate tools for different threats (e.g., API protection and a WAF). Instead, A10's real-time API protection solution looks at the holistic behavior of traffic and applies a single, intelligent security model to protect your web presence.

A10 Networks' security experts, Jamison Utter, Diptanshu Purwar, and Madhav Aggarwal, discuss the security challenges of AI. They discuss the new world of API-enabled AI agents and the necessity for robust security controls. Learn how to prevent misuse within the enterprise as they explore data ingress/egress and API security in the context of large language models (LLMs).

Beyond Guardrails: How to Secure Your AI from Unsanitized Data and Deceptive Prompts.

AI Agent Security: Verifying Workflows with AI Firewalls & Guardrails A10 security experts Jamison Utter, Madhav Aggarwal, and Diptanshu Purwar discuss the importance of context-aware security for AI agents. They emphasize that when automating workflows with AI, it's crucial to ensure that the context fed to the agents and their subsequent actions are verifiable and in line with existing company policies.

A10 security experts, Jamison Utter, Diptanshu Purwar, and Madhav Aggarwal explore the topic of securing AI agents, which they define as systems that perceive, decide, and act. They discuss: Defining AI Agents: Explaining that agents are not just chatbots, but are the "hands of AI" that can execute actions, call APIs, and automate complex workflows. The Challenge of Security: Discussing how security for AI agents goes beyond traditional model security and includes protecting against prompt injection, malicious instructions, and preventing unsafe actions or data leakage. The Importance of Context and Data.

The Invisible Trick: How to Fool an AI Agent A10 Networks' security experts, Jamison Utter, Madhav Aggarwal, and Diptanshu Purwar, discuss a classic example of an adversarial attack that tricks an AI agent using the equivalent of invisible watermarks. Madhav explains how researchers used an invisible watermark in a research paper that, when scanned by an AI agent, would automatically trigger a positive review. This watermark was not visible to human reviewers. This clever manipulation highlights a significant vulnerability in AI models: they can be influenced by hidden data in their input.

From Firewalls to AI: Understanding the Evolution of Cybersecurity The history of IT security has always been a journey of adapting to new threats. It started with simple firewalls to protect the "front door" and evolved to include endpoint, database, and Docker security. But what happens when the very intelligence you're building becomes a new kind of front door—and a new attack surface?

Securing AI Part 2: What Makes Protecting AI a Unique Challenge? In part 2 of our "Securing AI" series, security experts Jamison Utter, Diptanshu Purwar, and Madhav Aggarwal discuss the unique and evolving challenges of protecting AI systems, particularly Large Language Models (LLMs). They review why traditional security methods, like firewalls and simple behavioral analysis, fall short in a world where AI is dynamic, data-driven, and unpredictable.

Proactive Security: How ThreatX Protects Before an Attack Happens Carlo Alpuerto from A10 Networks highlights the core strengths of the ThreatX platform. He explains how ThreatX consolidates protection against WAF, API, DDoS, and bot attacks within a single, unified system. The platform's ability to use all of this information cumulatively is a key differentiator, allowing it to generate a risk score for specific entities and proactively protect against attacks, even during the initial reconnaissance and probing phases.

Context-Driven Guardrails: The Future of AI Security How do you protect AI and LLMs without slowing them down? A10 Networks' security experts Jamison Utter, Madhav Aggarwal, and Diptanshu Purwar share why context-driven guardrails are the future of AI security.

A10's Hybridization Strategy and the Evolving ThreatX Platform In this video, A10's Carlo Alpuerto discusses the company's commitment to continuously evolving its security solutions, especially following the acquisition of ThreatX. He highlights that a key benefit of the acquisition is the significant amount of developmental and testing resources that A10 provides, which will drive the future of the ThreatX platform.

The Swiss Cheese Model of AI Security A10 Networks' security experts, Jamison Utter, Madhav Aggarwal, and Diptanshu Purwar, explain that adequate AI security isn't a one-size-fits-all solution. They introduce the concept that security controls must be tailored to your specific data, company, and industry, as every context is unique.