Launch agentic AI with confidence. Watch our on-demand webinar to learn how. Watch it Now

Home | Blog | Author | Phillip Johnston
Avatar Phillip Johnston

Phillip Johnston

articles icon 11 Articles

Phillip's Articles
Artificial Intelligence

New York RAISE Act Ushers in a New Era of AI Transparency

See how the RAISE Act aims to stop AI-enabled crises.
June 17, 2025 Reading time 5 min read
Read More
Agentic AI, Artificial Intelligence

Your AI Is Talking. But Is It Saying the Right Things?

Learn how AI systems misbehave when prompted in one of the most dangerous threat areas: high-risk CBRN. Based on ActiveFence’s internal testing…
June 17, 2025 Reading time 5 min read
Read More
Artificial Intelligence

Seeing AI Security Through a Broader Lens

Threat actors are exploiting GenAI in the wild. Learn why true AI security must extend beyond infrastructure to detect and prevent real-world…
May 28, 2025 Reading time 6 min read
Read More
Artificial Intelligence

The Role of Organic and Synthetic Data in AI Safety and Security

See why AI safety teams must apply rigorous testing and training with diverse organic and synthetic datasets.
April 1, 2025 Reading time 5 min read
Read More
Artificial Intelligence

Why Red Teaming Is Critical for Generative AI Safety, Security, and Success

Discover principles followed by the most effective red teaming frameworks.
March 27, 2025 Reading time 6 min read
Read More
Artificial Intelligence

Key Security Risks Posed by Agentic AI and How to Mitigate Them

Explore the primary security risks associated with Agentic AI and strategies for effective mitigation.
March 13, 2025 Reading time 5 min read
Read More
Artificial Intelligence

The Importance of Threat Expertise in GenAI Red Teaming

Dive into why deep threat expertise on GenAI red teams is increasingly important.
March 6, 2025 Reading time 6 min read
Read More
Artificial Intelligence

LLM Guardrails Are Being Outsmarted by Roleplaying and Conversational Prompts

LLM guardrails are being bypassed through roleplay. Learn how these hacks work and what it means for AI safety. Read the full…
June 19, 2025 Reading time 8 min read
Read More
Agentic AI, Artificial Intelligence

ActiveFence Continues to Power Safety-First Enterprise AI with NVIDIA

Live from NVIDIA GTC 2025 in Paris - Discover how ActiveFence is partnering with NVIDIA to embed safety and security into enterprise…
June 11, 2025 Reading time 5 min read
Read More
Agentic AI, AI Red Teaming, Artificial Intelligence

ActiveFence Powers the AI Safety Flywheel with NVIDIA

Explore the AI Safety Flywheel from ActiveFence and NVIDIA and see how we keep AI safe at scale.
June 11, 2025 Reading time 9 min read
Read More
Artificial Intelligence

How a Rhyme-Driven Jailbreak Slipped Past GenAI Guardrails

See how easily multiple GenAI models, from LLMs to speech-to-speech, were tricked into divulging malicious code and weapon design instructions.
May 27, 2025 Reading time 6 min read
Read More

Other Authors

ActiveFence Staff

Visit page

Alaa Marzuk

Visit page

Amit Dar

Visit page

Ariel Koch

Research Lead

Visit page

Ariella Rothschild

Visit page

Avi Jager

Visit page

David Reis

Network Analysis Team Lead [Info-Ops]

Visit page

Dennis Kahn

Disinformation Research Team Lead

Visit page

Gideon Freud

Visit page

Guy Paltieli

Visit page

Ilana Berger

Visit page

Inbal Goldberger

Visit page

Jacob Steinblatt

Mobile Extremism Team Lead

Visit page

Kavya Sharma

Visit page

Liron Hakim Bobrov

Visit page

Maya Lahav

Visit page

Michal Brand Gold, General Counsel

Visit page

Milan Czerny

Visit page

Nitzan Tamari

Visit page

Noam Schwartz

Visit page

Noam Bar

Visit page

Phillip Johnston

Visit page

Sari Berkovich

Intelligence Writer

Visit page

Sean Boddy

Visit page

Shoshana Kranish

Visit page

Tal Langer

GenAI Red Teaming, Lead

Visit page

Tim Torres

Content Marketing Manager

Visit page

Left arrow Right arrow