Tag: LLM Security

RVAsec 15 Speaker Feature: Paul Brownridge

May 7, 2026
Speaker

Flirting with AI: Pwning web sites through their AI chatbot agents and politely breaking guard rails (<– add to your schedule)

Find out how to penetration test an AI chatbot.

Paul Brownridge:
Paul Brownridge is Head of Technical Delivery at Pen Test Partners, the ethical hacking firm. Originally from an engineering background, Paul swapped his hard hat for a white hat and has been working in cyber security for the last 10 years. His practical experience of industrial environments and cyber security make for a capable and highly competent OT cyber engineer. Paul is a regular speaker at national and international technology and security events such as Defcon and the (ISC)2 Security Conference, highlighting key risks with the internet of things, automotive and maritime.

Come see Paul Brownridge at RVAsec 15!

RVAsec 15 Speaker Feature: Jason Ross

May 6, 2026
Speaker

Social Engineering The Machine: When Your Target Runs On Attention Instead Of Anxiety (<– add to your schedule)

Every AI talk this year will tell you prompt injection is a problem. This one gives you the methodology to actually exploit it. Borrowing from decades of adversarial human testing, we’ll move past “vibes” and “jailbreak screenshots” to build a working, repeatable framework for social engineering the machine.

Jason Ross:
With 20+ years in cyber security, Jason Ross now performs adversarial testing and defense of deployed generative AI applications, agentic systems, and the LLMs powering them at Salesforce. Jason’s work focuses on prompt injection attacks and defense, model governance and security, and agent exploitation on high-stakes, high-visibility production deployments. He is also a core contributor to the adversarial AI tooling and datasets used by engineering, AI research, and ethics teams across the company.

Outside Salesforce, Jason co-leads the OWASP GenAI Security Project Red Team Initiative and helped author the OWASP GenAI Red Teaming Guide. He speaks regularly at industry conferences, including NDC Security, the SANS AI Security Summit, the OWASP GenAI Summit at RSA, Skytalks, RVASec, and more.

When he’s not breaking AI, Jason gives back to the security community as a staff member at BSidesLV and a volunteer at DEF CON.

Come see Jason Ross at RVAsec 15!

RVAsec 15 Speaker Feature: Brian Cardinale

May 5, 2026
Speaker

I Called Your AI Agent and It Told Me Everything: Live Voice AI Red Teaming (<– add to your schedule)

You’ll leave this talk understanding:
– How voice AI agents are architecturally different from text chatbots
– The specific attack vectors unique to voice: transcription manipulation, DTMF injection, audio-layer prompt injection, and social engineering through vocal tone
– A repeatable methodology for testing voice AI systems in your own organization
– Concrete remediation strategies for the most common findings

Brian Cardinale:
Brian Cardinale is the Principal Security Researcher at SecureCoders and creator of the TEAPOT methodology for voice AI red teaming. He holds a CISSP and has spent his career breaking things that aren’t supposed to break. Brian built VoiceGoat, the first open-source vulnerable voice AI agent, and leads RedCaller’s research into adversarial testing of phone-based AI systems. He previously discovered CVE-2015-4670 and has conducted security assessments across financial services, healthcare, and critical infrastructure. When he’s not social engineering robots over the phone, he’s probably social engineering robots over the phone.

Come see Brian Cardinale at RVAsec 15!