Secure AI Summit 2024 (Powered by Cloud Native)
2024-06-25
Seattle, United States
who it's for
cloud security engineers, platform engineers, security architects, security researchers, site reliability engineers, incident responders
topics
LLM supply chain security; RAG architecture threat modeling; AI-driven cloud threat hunting; model signing and provenance; open source LLM kill chains; zero trust with mTLS and Kyverno; chaos engineering for LLMs; RAG and agent application hardening; data loss prevention with embeddings; TorchServe remote code execution
| title | author | length |
|---|---|---|
| Opening Remarks | Shane Lawrence, Annie Talvasto | 05m |
Opening remarks set the day’s agenda with an AI Security focus and a call to join cloud native TAGs and working groups via Slack, list specific sessions… | ||
| Invisible Infiltration of AI Supply Chains: Protective Measures from Adversari... | Torin van den Bulk | 34m |
Threat modeling of an intentionally reductionist RAG reference architecture uncovers five concrete risks: proprietary data leaked to external SAS inference… | ||
| Elevate Cloud Threat Hunting with AI | Kenneth Peeples, Maya Costantini | 29m |
Kestrel as a Service deploys a composable threat‑hunting language plus a machine interpreter in containers and Kubernetes (MiniKube, OpenShift, Podman/Docker)… | ||
| Lightning Talk: Navigating the Intersection: AI’s Role in Shaping the Secure Open Sour... | Harry Toor | 17m |
The talk maps four concrete intersections: open source packages underpin AI systems and face supply‑chain risk, with tools like Scorecard giving point‑in‑time… | ||
| Future Open Source LLM Kill Chains | Vicente Herrera | 32m |
Claim: an advanced, patient adversary can weaponize open-source LLMs and their supply chain by becoming maintainers, publishing tainted models, or adding… | ||
| Toward Zero Trust with AI | Boris Kurktchiev, Ronald Petty | 38m |
Cloud-native Zero Trust is framed as practical steps not theory: mTLS via Istio for identity, Kyverno for policy governance and mutation, and K8sGPT for a… | ||
| Security-Focused Chaos Engineering - the Lasso for AI Security T... | Priyanka Tembey, Glenn McDonald | 29m |
An open source framework called Secops-Chaos encodes OWASP LLM risks and MITRE ATLAS TTPs as executable YAML experiments that run in Kubernetes and use… | ||
| Secure by Design: Strategies for LLM Adoption in Cloud-Native Environm... | Patryk Bąk, Marcin Wojtas | 37m |
Built a cloud‑native RAG/agent platform, aligned threat modeling to OWASP Top 10 for LLMs and runs garak and Gizard scans against RAG apps using the Tesla… | ||
| Lightning Talk: Revolutionize Security GRC: Leverage AI and LLM for Continuous Control... | Megha Shah | 12m |
Claims a pipeline that converts PDFs to YAML (example: NSA Kubernetes hardening) and builds a Neo4j graph that links a GRC schema to a system schema… | ||
| Using Large Language Models to Improve Data Loss Prevention in Organizations | Asaf Fried | 25m |
Cato Networks deploys a fine‑tuned LLM that classifies sensitive documents by creating embeddings and using triplet loss to push same-category items together… | ||
| ShellTorch the Next Evolution in *4Shell Executions | Gal Elbaz, Avi Lumelsky | 33m |
A chain of four vulnerabilities yields full RCE against TorchServe, documented as CVE-2023-43654 with CVSS 9.8, and tens of thousands of instances exposed; the… | ||
| Closing Remarks | Shane Lawrence, Annie Talvasto | 01m |
Slides appear on the conference schedule within days and session recordings go to a CNCF YouTube playlist in a couple of weeks, so replay is available. One… | ||
| nothing matches | ||