SEC536: Adversarial AI - Penetration Testing AI Systems

In-Person
In-Person
In-Person & Virtual
Organizations are deploying autonomous AI agents into production at scale: agents that authenticate, execute multi-step workflows, and make decisions across cloud infrastructure. These agents operate at machine speed, which means security operations must too.
In-Person & Virtual
The rapid shift to autonomous AI agents in the cloud is accelerating security concerns. Traditional, human-centric systems are overwhelmed by the millions of new digital identities agents create, exacerbating issues like compromised identities (the source of over 70% of cloud breaches) and sophisticated agent hijacking attacks.
In-Person & Virtual
In-Person & Virtual
Agentic AI represents a structural shift in enterprise software, not an incremental improvement. For decades, organizations built security frameworks around a foundational assumption: humans make decisions, machines execute them. Agentic systems invert that model. They reason, plan, and act autonomously across identities, data stores, tools, and other agents, operating at machine speed in environments designed for human-paced decisions.
In-Person & Virtual
Fireside Chat with AWS, Google and Microsoft Keynote Speakers
In-Person & Virtual
In-Person & Virtual
In-Person & Virtual
In-Person & Virtual
In-Person & Virtual
Step into the future of cyber defense. This hands-on experience is designed for security practitioners ready to move beyond AI hype into real-world application. Learn how AI agents can help you investigate, triage, and respond to threats at machine speed through practical exercises, real-world scenarios, and an interactive CTF challenge.
In-Person
In-Person
In-Person
In-Person
In-Person
In-Person & Virtual
We'll cover the latest on AI-enabled nation state activity from Anthropic's view, including Mythos-class models; frontier model cyber capabilities to help defenders succeed against AI-augmented attacks; and what the future of model scaling has in store for cyber, engineering, and SDLC right around the corner.
In-Person & Virtual
Machine identities now vastly outnumber humans in most Azure tenants, and they are routinely over-permissioned, long-lived, and sparsely monitored. When a service principal deletes diagnostic settings or a managed identity writes to a storage account, the analyst staring at the Activity Log has to answer a deceptively hard question: which identity actually did this, and on whose behalf?
In-Person & Virtual
Most teams integrating LLMs into cloud applications are flying blind in their pipelines. They have added scanners and perhaps some guardrails, but they do not actually know whether those controls hold up against real attacks. This session explores a practical approach to closing that gap.
In-Person & Virtual
In-Person & Virtual
In-Person & Virtual
While the security community remains hyper-focused on LLM-specific threats like prompt injection, real-world enterprise deployments reveal that the most critical vulnerabilities often lie in the underlying architecture. This session explores hard-learned lessons from several Generative AI (GenAI) deployments, moving past theoretical risks to address the infrastructure failures that break production environments.
In-Person & Virtual
When an AI is 70% accurate at automating each task of a 10-task investigation, 97% of cases end up incomplete, and that is the optimistic scenario. This session explores efforts to close that gap for cloud and SOC investigations.
In-Person & Virtual
In-Person & Virtual
In-Person
Step into the future of cyber defense. This hands-on experience is designed for security practitioners ready to move beyond AI hype into real-world application. Learn how AI agents can help you investigate, triage, and respond to threats at machine speed through practical exercises, real-world scenarios, and an interactive CTF challenge.
In-Person
In-Person
In-Person
Generative AI is quickly becoming a default part of the software development lifecycle. Faster delivery can also increase security risk, operational fragility, and decisions that are difficult to review or audit after the fact.
This session focuses on AI coding guardrails: practical, developer-friendly controls that help teams adopt coding assistants with confidence while maintaining strong security, governance, and assurance. We will walk through four maturity levels for agentic coding controls.
In-Person & Virtual