Trusted by Anthropic, Google, and Cohere, Alice brings nearly a decade of real-world adversarial intelligence to frontier AI - and is approaching $100M in ARR.
Alice works to protect artificial intelligence models from misuse and rogue behavior, and has raised $140 million after a spate of high-profile hacks from AI systems.
ynetnews examines recent tests in which AI agents exploited security flaws and reached systems beyond their evaluation environments. Alice CEO Noam Schwartz explains why these are containment failures rather than escapes, and why fast-advancing offensive capability is the more urgent risk.
Newsweek explores the gap between polished AI demonstrations and the realities of enterprise deployment. Alice CEO Noam Schwartz explains why successful demos often fail to reveal critical security, governance, and operational challenges that emerge in production.
The Washington Post examines the evolving challenge of AI jailbreaks and the limitations of current model safeguards. Alice CEO Noam Schwartz explains why perfect jailbreak resistance remains elusive and how the emerging AI security industry is helping organizations manage these risks.
Intake on Alice's Heretic's research: Open-weight AI models with advanced capabilities and no safeguards are becoming much more accessible. While they can be useful, AI safety experts have concerns.
