Truth Behind the Hack: Experts Break Down AI Red Teaming in a Live Q&A

March 21, 12pm ET | 5pm GMT 

As artificial intelligence becomes increasingly integrated into our digital landscape, it brings a host of new security challenges and ethical considerations. Join this "Ask Me Anything" (AMA) session with three ethical hackers specializing in AI security and safety. They’ll answer your pressing questions about the complex world of AI, including generative AI and machine learning, security testing implications, and AI red teaming for organizations with complex AI systems or adopting AI, from customer-facing chatbots to internal LLMs (large language models). Gain hackers’ insights into how to protect your AI systems from emerging threats while ensuring AI’s safe and responsible use.

Who should join:

  • Cybersecurity leaders and practitioners aiming to navigate AI's impact on security practices, while ensuring secure AI deployment
  • AI developers and engineers looking to deepen their knowledge of securing AI through APIs, access controls, and encryption
  • Business leaders and decision-makers overseeing the adoption of AI in their operations
  • Legal and compliance professionals focusing on mitigating AI-related financial risks, including legal penalties and reputational damage

What we’ll cover:

  • The latest trends in AI vulnerabilities, including model inversion, data poisoning, and adversarial AI attacks
  • Best practices for AI security to protect user information and maintain system integrity
  • Guiding principles for responsible AI implementation to prevent misuse and ensure compliance with developing governance policies
  • The role of Red Teaming in identifying and mitigating risks in AI implementations
  • The importance of incident response automation and how AI-driven solutions can enhance threat detection and analysis
  • Real-world use cases demonstrating the impact of AI on cybersecurity

Watch on demand

Katie Paxton-Fear

Katie Paxton-Fear

Katie is a hacker who specializes in AI and API vulnerabilities. When she is not hacking she is probably making videos teaching people how to hack or making lucky socks!

Katie is a doctor and recently got her PhD in cyber security. Her full-time job is as a lecturer at a university. Her full-time job is also her hobby, and her hobby gets to be part of her full-time job.  She loves teaching students with H101 and being able to teach them about real security flaws from real companies!

Joseph Thacker

Joseph Thacker

Joseph is a security researcher who specializes in application security and AI. He’s helped Fortune 500 companies find vulnerabilities that could have cost them millions in lawsuits or reputation. He’s submitted or collaborated on over 1,000 vulnerabilities across Hackerone and Bugcrowd. Companies and developers make the same mistakes over and over. He loves helping find those issues whether it’s via hacking, teaching, or consulting. Reach out if you’d like to know more.

Joseph has spent time as a Security Analyst, Engineer, and Researcher. His certifications and degrees include:

  • Master of Science in Cybersecurity and Information Assurance
  • Bachelor of Science in Computer Science
  • Certified Information Systems Security Professional (CISSP)
  • Certified Ethical Hacker (C|EH)
  • Computer Hacking Forensic Investigator (C|HFI)
  • CompTIA Security+
Dane Sherrets
Senior Solutions Architect

Dane Sherrets

Dane Sherrets is an experienced Senior Solutions Architect at HackerOne, helping large enterprises and governments to successfully leverage bug bounty programs and ethical hacking services to best minimize growing cyber risks. Prior to joining HackerOne, Dane worked as a mobile application security specialist helping organizations utilize tools to uncover vulnerabilities in their mobile apps. Dane is passionate about leveraging advancements in cryptography to preserve privacy on the internet. Dane enjoys bug bounty hunting and tinkering with EVM-based smart contracts in his free time.