TrojAI’s cover photo
TrojAI

TrojAI

Software Development

Saint John, New Brunswick 5,491 followers

You’re innovating with AI. We’re securing it.

About us

Securing AI Models and Applications from Development to Deployment TrojAI helps the world’s leading enterprises secure the behavior of their AI/ML and GenAI models and applications. Our best-in-class AI security platform empowers enterprises to safeguard AI models and applications at both build time and run time. - TrojAI Detect automatically red teams AI models during development, providing remediation guidance at build time. - TrojAI Defend acts as a firewall for AI to protect against real-time threats. With comprehensive security at every stage, TrojAI ensures robust protection for AI models and applications. Schedule a time to chat with us to learn more at https://www.troj.ai/contact-us

Website
http://troj.ai
Industry
Software Development
Company size
11-50 employees
Headquarters
Saint John, New Brunswick
Type
Privately Held
Founded
2019
Specialties
artificial intelligence, cybersecurity, and ai security

Locations

Employees at TrojAI

Updates

  • Today is Pi Day! It’s celebrated on March 14 (3/14) to match the first three digits of π. It also happens to be Albert Einstein’s birthday! Here are some other fun facts about pi: ➕ Pi’s decimal expansion never ends. Mathematicians have computed trillions of digits of π, but there’s no pattern! 🧠 The record for memorizing pi goes to Rajveer Meena who recited 70,000 digits of π from memory in 2015! 🥧 3.14 spells PIE upside down. If you look at "3.14" in a mirror, it somewhat resembles the word "PIE." 🧮 You only need 39 digits. For most calculations involving the universe, just 39 digits of π are enough to achieve accuracy greater than the known size of the observable universe. 🚀 NASA engineers use about 15 decimal places of π for their space calculations. 🍕 You can approximate pi with pizza – If a pizza has a radius "z" and height "a," its volume is π * z² * a (which spells "pizza" mathematically). 💻 Computers love calculating pi – Some of the most powerful supercomputers have been used just to compute more digits of π. 🏴󠁧󠁢󠁷󠁬󠁳󠁿 The symbol π is over 300 years old. It was first used in 1706 by the Welsh mathematician William Jones. 🧪 A famous probability experiment, Buffon’s Needle experiment, involves dropping needles on a lined sheet of paper, and the probability of them crossing a line is related to π! ⚖️ In 1897, an Indiana legislature almost passed a bill legislating the value of π as 3.2! Enjoy this day of irrational and transcendental fun! #Pi #PiDay #TrojAI #AISecurity #Cybersecurity

    • No alternative text description for this image
  • New Blog Alert: Understanding AI Jailbreaking & How to Prevent It As AI adoption accelerates, so do the risks of AI jailbreaking. AI jailbreaking is a growing security threat where attackers manipulate AI models to bypass built-in security guardrails. This can lead to misinformation, security breaches, or ethical concerns that impact businesses and users alike. 🔎 In our latest blog, we break down:  💚 What AI jailbreaking is and how it differs from prompt injection  💚 Examples of jailbreaking attacks  💚 The risks of jailbroken AI models  💚 Key strategies to detect and prevent these threats At TrojAI, we’re committed to securing AI models and applications against adversarial threats to help enterprises build secure, safe, and reliable AI. 🔗 Read the full blog here: https://lnkd.in/dS_YhhnJ Have thoughts on AI jailbreaking? Let’s discuss in the comments! 👇 #AI #CyberSecurity #TrojAI #AISafety #MachineLearning #Jailbreaking

    • No alternative text description for this image
  • It's been an incredible week of connecting and learning at the FS-ISAC Americas Spring Summit in New Orleans! ⚜️🎭 TrojAI was proud to sponsor the signature event at Generations Hall last night, but even more rewarding was the opportunity to engage with so many financial services security experts. The rapid expansion of AI in the enterprise brings both innovation and risk. Christian Falco and Or Brown had many insightful conversations about how organizations can stay ahead of emerging threats. At TrojAI, we're committed to tackling these AI security challenges head-on. Laissez les bon temps rouler! Until next time New Orleans! 🎷 🎹 🎺 🥁 #FSISAC #TrojAI #AISecurity #FinancialServices #GenerationsHall

    • No alternative text description for this image
    • No alternative text description for this image
    • No alternative text description for this image
  • 🤖 Agentic AI is a game-changer, but also a security minefield. These autonomous systems don’t just follow rules; they rewrite them. That’s a hacker’s dream and a major headache for security pros. We need: 🔐 Zero-trust for AI 🛡️ Memory hygiene 📊 Multi-layered monitoring Without guardrails, we’re looking at a runaway 🏃♂️➡️ threat landscape. Are we ready? Let’s talk AI security. #CyberSecurity #AI #TrojAI #AgenticAI

    View profile for James Stewart, Ph.D.

    AI Security for the Enterprise

    🔥 𝗛𝗼𝘁 𝗧𝗮𝗸𝗲 𝗧𝘂𝗲𝘀𝗱𝗮𝘆𝘀 🔥 Agentic AI: The Future of Automation… or a Security Nightmare? Agentic AI is here, and if you’re not paying attention, you’re already behind. Unlike traditional AI, which plays within the lines, agentic AI doesn’t just follow rules—it makes its own. These AI-driven agents perceive, reason, act, and adapt with minimal human oversight. Sounds powerful? It is. Sounds dangerous? Also yes. 💀 𝗪𝗵𝘆 𝘀𝗵𝗼𝘂𝗹𝗱 𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗽𝗿𝗼𝘀 𝗰𝗮𝗿𝗲? Because these autonomous systems are a hacker’s dream and a CISO’s worst nightmare. We’re talking goal manipulation, memory poisoning, and cascading hallucinations—attacks that can rewrite objectives, taint decision-making, or create a runaway feedback loop of bad intel. 🔐 So, what’s the game plan? We need an AI security-first approach—before these agents go rogue. That means: ☑️ 𝗭𝗲𝗿𝗼-𝘁𝗿𝘂𝘀𝘁 𝗳𝗼𝗿 𝗔𝗜: Treat agentic AI like an untrusted entity (because it is). ☑️ 𝗠𝗲𝗺𝗼𝗿𝘆 𝗵𝘆𝗴𝗶𝗲𝗻𝗲: Guard against data poisoning and unauthorized access. ☑️ 𝗠𝘂𝗹𝘁𝗶-𝗹𝗮𝘆𝗲𝗿𝗲𝗱 𝗺𝗼𝗻𝗶𝘁𝗼𝗿𝗶𝗻𝗴: Don’t just log outputs—watch how agents reason and adapt. Agentic AI is the future, but without guardrails, it’s a loaded weapon with a mind of its own. The security industry needs to move fast—or risk playing catch-up when things go sideways. Are we ready for agentic AI security threats? Let’s talk TrojAI. 🔽 #Cybersecurity #AgenticAI #AIThreats

    • No alternative text description for this image
  • TrojAI is thrilled to be included on James Berthoty | Latio Tech's list. If you're interested in learning how to protect your AI models and applications from risks and attacks with a comprehensive AI security platform, talk to us! #AISecurity #Cybersecurity #TrojAI #AgenticAI #GenAI

    View profile for James Berthoty

    Security Engineer Turned Industry Analyst @ Latio Tech | AWS Community Builder

    Introducing over 30 new vendors to the Latio List! The goal of the Latio Tech list is to be a living, accurate, curated place to find security tools in a clear, engineering focused way. Today we launched a massive update with over 30 new vendors, 3 new categories, and numerous performance improvements. Here they all are below, probably pouring over into the comments! You can view the list here: https://list.latio.tech/ High level changes: 1. Added new categories: Asset Management, Data Security, SaaS Security 2. Renamed Remediation Platforms to Vulnerability Management (CTEM) 3. Added new "hands-on" tag to indicate which tools we've been hands on with, and made this a requirement for Latio's Choice. 4. Massive Javascript optimizations improving site speed Vendors added: 1. Added Exaforce to boundary breakers - AI + data lake for SOC to level up across the board 2. Added Cytix to boundary breakers - monitors places where change happens for on demand pentesting of new endpoints 3. Added TrojAI to LLMs - runtime testing and protection for LLMs with on-prem hosting 4. Added Marqus AI to LLMs - runtime security for LLMs 5. Added BlueFlag Security to ASPM and cloud identity - identity based ASPM and detection, JIT for git 6. Added Rainforest Technologies to ASPM - code security with brand protection, hosted via on-prem vm 7. Added Fluid Attacks to ASPM - ASPM scanning + services 8. Added ZeroPath to Code-fixers - AI SAST = the next generation, no cap 9. Added Appdome to Mobile - the most robust mobile app runtime protection 10. Added Formal to the new data category - awesome runtime data aliasing 11. Added Teleskope to the new data category - data access control for data stores and SaaS 12. Added Cyera to Data - classical DSPM 13. Added Jamf to new MDM category - the apple MDM king 14. Added Kandji to the new MDM category - the strong jamf alternative 15. Added Evren to the new MDM category - a smart developer MDM alternative to virtual machines 16. Added JupiterOne to the new Asset Management category - great all in one queryable and customizable asset management 17. Added Axonius to the new Asset Management category - Great asset and vulnerability management capabilities 18. Added Cortex by Palo Alto Networks to CDR - now it works with cloud 19. Added Mondoo to Vuln Mgmt - ambitious all in one vulnerability scanning and management 20. Added Conviso Application Security to Vuln Mgmt - vulnerability management + services

  • At TrojAI, we’re committed to building robust defenses against adversarial AI to ensure the security of AI models and applications. Honored to be included in this important work. We appreciate the recognition! #AI #Cybersecurity #TrojAI #AIThreats #GenAI

    View profile for Francis Odum

    Founder @ Software Analyst Cybersecurity Research

    New Research Alert: Very Excited to share one of the most comprehensive reports on securing enterprise AI. Security leaders are facing a wave of AI developments—from DeepSeek to Manus AI—that raise concerns about data leaks, model integrity, and more. This research covers: ▪️ The state of AI adoption and its security risks ▪️ Why traditional cybersecurity controls (e.g., firewalls) fall short ▪️ A framework for understanding AI security solutions ▪️ Insights from security leaders on what works Our recommendations, based on extensive discussions with security leaders and practitioners: 1️⃣ Start with data security controls – AI security is a data security problem first. 2️⃣ Prioritize runtime security – eBPF-based solutions offer the strongest observability. 3️⃣ Implement Governance controls - Always scan and maintain a full inventory of all AI (especially shadow AI). We anticipate more Chinese AI developments that will increase US open-source adoption, driving the need for securing AI. 4️⃣ Shortlist vendors carefully – The market is fragmented, but key players stand out. Today's Market Landscape & Solutions: There are over 50+ vendors vying for CISOs’ attention - a nightmare for CISOs, but most fall into two broad categories. We specifically highlight 9 leading vendors with extensive customers, traction and promising use cases (this categorization is not exhaustive): 1. Securing AI Product Lifecycle (and our opinion) ◼️ Palo Alto Networks – strong AISPM built on the Strata Firewall ◼️ Protect AI - strong open-source work and threat research ◼️ HiddenLayer – strong scanning and D&R capabilities ◼️ Noma Security - strong partnerships with large ML providers and coverage ◼️ Pillar Security – strong lifecycle capabilities and adaptive guardrails ◼️ TrojAI – strong pen-testing for homegrown AI applications *Observation : Protect AI and HiddenLayer currently lead in customer traction based on our research. 2. Securing Employee AI Usage (and our opinion) ◼️ Prompt Security – strong on GitHub Copilot and securing employee AI ◼️ WitnessAI AI – strong policy enforcement and SASE integration ◼️ Zenity – strong in M365 and agentic app security We go much DEEPER on strengths and trade-offs of all these leading vendors within the report. If you're evaluating AI security vendors for a POC, these are some of the names that should come first. We also highlight all the 50+ vendors in the report. We believe this is one of the most detailed analyses on this topic. If you're a security leader, this is for you. Full report: https://lnkd.in/eAyBHtvp * Massive thank you to Allie Howe for collaborating on this research and my amazing team for their hard work. Please read, and let us know your thoughts. Special thanks to the CISOs and practitioners who shared their thoughts / contributed to this research.

    • No alternative text description for this image
  • We are so excited to announce that our CTO James Stewart, Ph.D. will be participating in this important discussion on the power of early-stage support for startups in New Brunswick. Check out the link below to register!

    🎤 PANELIST ANNOUNCEMENT! We're pleased to announce that Dr. James Stewart, Ph.D., CTO of TrojAI will be one of the panelists for 'The Power of Early-Stage Support: Fueling Bold Ideas & Future Success'. James will be sharing his experience as a serial entrepreneur on how early investment, mentorship, and strategic connections fueled his companies startup growth and innovation. 📅 Don’t miss out! Register now to hear how early-stage support is a game-changer for innovation at Breakthru: https://lnkd.in/emeqUxUn #NBIF #Breakthru #Cleantech #Innovation #AI #Startups

    • No alternative text description for this image
  • 💫 TrojAI is heading to NVIDIA GTC! 💫 We’re excited to announce that TrojAI will be attending the NVIDIA GTC AI Conference in San Jose, California, from March 17–21, 2025! 🎉 As a proud Microsoft for Startups, Pegasus Program partner, TrojAI is excited to demoing out AI security platform at the Microsoft booth on: 📅 Wednesday, March 19 | 12:00 – 2:00 PM 📅 Thursday, March 20 | 12:00 – 2:00 PM Our cutting-edge platform helps protect AI models and applications from adversarial threats, ensuring security and trust in AI systems. If you're attending #GTC25, be sure to stop by and see how we’re shaping the future of AI security! 🤝 Let’s connect and talk AI security! Who else is attending? #NVIDIA #TrojAI #MicrosoftForStartups #PegasusProgram #AI #Cybersecurity #AISecurity

    • No alternative text description for this image
  • 🚀 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜: 𝗧𝗵𝗲 𝗙𝘂𝘁𝘂𝗿𝗲 𝗶𝘀 𝗛𝗲𝗿𝗲...𝗕𝘂𝘁 𝗔𝗿𝗲 𝗪𝗲 𝗥𝗲𝗮𝗱𝘆 𝗳𝗼𝗿 𝘁𝗵𝗲 𝗥𝗶𝘀𝗸𝘀? 🤖⚠️ AI isn’t just about chatbots and simple automation anymore. Agentic AI - AI that acts autonomously, adapts dynamically, and makes independent decisions - is taking center stage. Powered by Large Language Models (LLMs) and generative AI, these systems can execute complex, multi-step tasks 𝘸𝘪𝘵𝘩𝘰𝘶𝘵 𝘤𝘰𝘯𝘴𝘵𝘢𝘯𝘵 𝘩𝘶𝘮𝘢𝘯 𝘰𝘷𝘦𝘳𝘴𝘪𝘨𝘩𝘵. Sounds futuristic? It’s already happening. But here’s the catch: 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 𝗰𝗼𝗺𝗲𝘀 𝘄𝗶𝘁𝗵 𝗻𝗲𝘄 𝗿𝗶𝘀𝗸𝘀 like excessive agency, memory poisoning, and cascading hallucinations. Traditional security approaches aren’t enough. 𝗪𝗲 𝗻𝗲𝗲𝗱 𝗮 𝗻𝗲𝘄 𝗔𝗜 𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗽𝗹𝗮𝘆𝗯𝗼𝗼𝗸. 🛡️ Phil Munz, Senior Manager, Data Science at TrojAI, breaks it all down in our latest blog, 𝘼𝙜𝙚𝙣𝙩𝙞𝙘 𝘼𝙄: 𝙐𝙣𝙙𝙚𝙧𝙨𝙩𝙖𝙣𝙙𝙞𝙣𝙜 𝙄𝙩𝙨 𝙀𝙫𝙤𝙡𝙪𝙩𝙞𝙤𝙣, 𝙍𝙞𝙨𝙠𝙨, 𝙖𝙣𝙙 𝙎𝙚𝙘𝙪𝙧𝙞𝙩𝙮 𝘾𝙝𝙖𝙡𝙡𝙚𝙣𝙜𝙚𝙨. It covers: 🔍 𝗛𝗼𝘄 𝗱𝗼 𝘄𝗲 𝘀𝗲𝗰𝘂𝗿𝗲 𝗮𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜? 🔍 𝗪𝗵𝗮𝘁 𝗮𝗿𝗲 𝘁𝗵𝗲 𝗵𝗶𝗱𝗱𝗲𝗻 𝘁𝗵𝗿𝗲𝗮𝘁𝘀 𝗲𝗻𝘁𝗲𝗿𝗽𝗿𝗶𝘀𝗲𝘀 𝗻𝗲𝗲𝗱 𝘁𝗼 𝗽𝗿𝗲𝗽𝗮𝗿𝗲 𝗳𝗼𝗿? 🔍 𝗪𝗵𝘆 𝗶𝘀 𝗽𝗿𝗼𝗮𝗰𝘁𝗶𝘃𝗲 𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝘁𝗵𝗲 𝗼𝗻𝗹𝘆 𝘄𝗮𝘆 𝗳𝗼𝗿𝘄𝗮𝗿𝗱? If you’re working with AI or just curious about its next evolution, this is a must-read! 👉 Read now: https://lnkd.in/dU6YBxmM #AI #AgenticAI #TrojAI #CyberSecurity #AgenticAISecurity #GenAI #LLMs

    • No alternative text description for this image
  • 🔥 Couldn't agree more! 🔥 AI security isn’t a numbers game. It’s about real-world performance and honest evaluation. At TrojAI, we’re committed to cutting through the noise to deliver AI security solutions that actually work, not just look good on a slide deck. Let’s talk precision, recall, and real-world resilience. If your AI security vendor isn’t transparent about trade-offs, you're not talking to the right vendor. Follow TrojAI for more insights on securing AI in an adversarial world! #AISecurity #MLSecurity #HotTakeTuesdays

    View profile for James Stewart, Ph.D.

    AI Security for the Enterprise

    🔥 𝗛𝗼𝘁 𝗧𝗮𝗸𝗲 𝗧𝘂𝗲𝘀𝗱𝗮𝘆𝘀 🔥 AI Accuracy Metrics: The Art of Smoke & Mirrors Vendors love to throw around big numbers. “97% accuracy!” they’ll say, expecting you to nod along and sign the contract. But here’s the dirty little secret: that number is often meaningless. Why? Because accuracy can be gamed. Evaluate a model on the same benchmark data it was trained on? Boom—sky-high accuracy. Test it in a setting where it never sees edge cases? Flawless performance. And the worst offender? The “flag everything” approach—just classify everything as malicious, and suddenly, you “catch” every bad thing. Of course, the false positives make the system unusable, but hey, the metric looks great on a slide deck. Real AI security requires a breakdown of accuracy into recall (how much of the actual bad stuff we catch) and precision (how much of what we flagged is actually bad). If a vendor claims 97% recall AND precision, be skeptical—especially if they don’t give details about the use case. In fields like adversarial prompt detection, that’s far beyond state-of-the-art. Security isn’t about buying the best marketing—it’s about working with a team that understands what’s actually possible. Pick a partner who is transparent about trade-offs, understands the limitations, and is willing to collaborate on addressing your real-world requirements. Because in security, false confidence is even more dangerous than false negatives. Follow us over at TrojAI for more hot takes! #CyberSecurity #AI #MachineLearning #SecurityMetrics #CISO

    • No alternative text description for this image

Similar pages

Browse jobs

Funding

TrojAI 5 total rounds

Last Round

Seed

US$ 5.8M

See more info on crunchbase