Mace AI

Advancing trustworthy AI through adversarial testing and remediation.

[Mace AI @mace_ai_corp]

Binance says an internal AI tool was one of the steps in the theft of roughly $6.3 billion. We recreated that chain in simulated scenarios with Mace AI’s Fisher to see how AI agents hold up. The results and the checks to run are here: https://t.co/yYJK0YcfAX
#AIAgentSecurity #AgenticAI #maceai

[Mace AI @mace_ai_corp]

Trust is essential for financial institutions.

Our co-founder & Chief Scientist, @gregnfrank, is participating in the @Mastercard Trust at Risk Financial Institutions Cyber Roundtable for #B20USA

�� https://t.co/o88gchK9QV
#TrustAtRisk #AIagents #FinancialServices #MaceAI

[Mace AI @mace_ai_corp]

Your agents want to help. Even if that means helping an intruder.

If you've been putting off testing your agentic systems for vulnerabilities. Today should be your wake-up call.

[Roundtable Network @RTB_io]

WATCH: @mace_ai_corp founder Walton Comer explains how hackers behind Binance's $6.34 billion theft turned an internal AI tool against the exchange, and what other companies should learn from it.

[Mace AI @mace_ai_corp]

If @binance's agents are vulnerable, how confident are you in yours?

It's probably time to get your agents checked with Mace AI.

[Binance @binance]

https://t.co/sU9dUqLQDH

[Mace AI @mace_ai_corp]

University and industry partnerships should be standard practice as AI enters critical business workflows.

Watch Greg Frank and Walton Comer explain why Mace AI is funding doctoral research at @uvadatascience in @_cagarwal’s Aikyam Lab.

[Roundtable Network @RTB_io]

WATCH: Mace AI CEO Walton Comer and Chief Scientist Greg Frank explain why they're funding AI safety research at the University of Virginia.

In a conversation with James Heckman
@mace_ai_corp | @gregnfrank | @JamesCHeckman

[Mace AI @mace_ai_corp]

@_cagarwal @uvadatascience We truly feel that this work is a higher calling. Thrilled to be supporting the cause.

[Mace AI @mace_ai_corp]

We are excited to announce our partnership with University of Virginia's Aikyam Lab, part of the School of Data Science @uvadatascience, alongside @_cagarwal and @strnr.

The Mace AI Fellowship in Trustworthy Computing funds AI safety research at the school.

[Mace AI @mace_ai_corp]

Axios story here: https://t.co/yg8M4HpTEJ

[Mace AI @mace_ai_corp]

The White House mandated that AI reporting and remediation are "not optional."

Do you have the evidence and confidence needed to report an incident and mark it as "fixed"?

Our tool, Fisher, has you covered.

[Mace AI @mace_ai_corp]

How does a trusted AI agent become a “double agent”?

Walton Comer and @gregnfrank discuss how manipulation over several interactions can push agents beyond their authorized scope, with @JamesCHeckman on TheStreet Roundtable.

[TheStreet @TheStreet]

.@mace_ai_corp founders warn of AI double agents amid banks detecting unauthorized AI agents

https://t.co/AeOyZgQv5h

[Mace AI @mace_ai_corp]

@gregnfrank is quoted in MIT's @techreview on AI refusal and the risk of censorship. Who sets the rules matters as much as whether an AI follows them.

Arthur Holland Michel's article examines both questions.

https://t.co/Jogof8p8dR

[Mace AI @mace_ai_corp]

Your agents might be forming rogue swarms.

What can you do about it?

[Roundtable Network @RTB_io]

WATCH: Mace Ai's founders explain how OpenAI agents cheated on tests and why companies need independent security checks.

In a conversation with James Heckman.
@mace_ai_corp | @gregnfrank | @JamesCHeckman

[Roundtable Network @RTB_io]

WATCH: Mace Ai's founders explain how OpenAI agents cheated on tests and why companies need independent security checks.

In a conversation with James Heckman.
@mace_ai_corp | @gregnfrank | @JamesCHeckman

[Mace AI @mace_ai_corp]

Companies must be able to provide evidence if an incident occurs.

"This notification and remediation process is not optional," White House Super Intelligence Force leaders said in a statement shared exclusively with Axios [October, 2026].

[TheStreet @TheStreet]

.@mace_ai_corp founders on what OpenAI's Hugging Face breach means for businesses | @gregnfrank | @JamesCHeckman

https://t.co/Dgl9U8jedx