You can meet the Safeguard team at major security and software conferences across the year. The team also hosts smaller technical summits on supply chain security and AI security. If you'll be attending one of the events below, drop a note and we'll find time.
Live Griffin reasoning demo against a held-out CVE set. Talk: "Engine plus LLM beats pure-LLM bug hunters."
Partner-track demo of reachability-aware auto-fix in an AWS-native CI/CD pipeline.
Briefing on the security-only training corpus thesis and the Aegis attention pattern.
Workshop in the AI Village on adversarial prompt-injection eval methodology.
Live demo of self-healing container pipelines with Griffin auto-fix.
Talk: "Coordinated disclosure pipelines for zero-day candidates surfaced by reachability plus LLM hypothesis."
Where we've shown up over the last two years — booths, talks, panels, and community engagements across India, North America, and Europe.
Booth + speaking. Lit up the early Griffin reasoning trace demo on stage and showed the held-out CVE evaluation methodology. First public unveiling of Eagle as a standalone ranking model.
Briefing on the engine-plus-LLM thesis for software supply chain security. Heavy interest in the structured trace contract and the adversarial disproof pass. Slides published on the blog.
Two talks: one on the Griffin reasoning trace contract and one on adversarial robustness in security-tuned LLMs. Slides, demo notebooks, and the eval-set methodology published openly.
Return engagement with deeper coverage of cross-package taint chain reasoning and Griffin Zero's 256k-context retrieval gates. Live demo against a held-out exploit set.
Community-track talks on reachability + LLM bug hunting and on coordinated disclosure workflows. Hands-on workshop with the Safeguard CLI and the policy templates library.
Panel + booth focused on AI for security: the security-only training corpus thesis, MCP-server governance, and the practical economics of running reasoning models inside regulated environments. Strong engagement from Indian financial services and public sector attendees.
Workshop on integrating reachability analysis into existing SAST + SCA tool chains. Strong interest from financial services attendees on DORA evidence pipelines.
Lightning talk on MCP-server governance and sensitive-data egress guardrails. The open-source policy templates library was released after the event in response to attendee feedback.
Invitation-only, quarterly, virtual. CISO and head-of-AppSec level discussion. No vendor pitches; structured agenda on a single supply-chain topic per session.
Annual, hybrid. Focused on AI for security research. Open submissions for short technical talks. Research-day proceedings published openly.
Annual, in-person. For federal and regulated public-sector audiences. Boundary-aware deployment patterns, accreditation, and sovereign AI.
If your event needs a speaker on one of these, get in touch.
How engine-plus-LLM pipelines outperform either approach alone, with evaluation methodology.
Running the full Griffin lineup including Zero (671B-MoE) in air-gapped and STQC-aligned environments.
Tool allowlisting, capability scoping, sensitive-data egress guardrails, and prompt audit log design.
Why training narrowly on cybersecurity data changes the precision/refusal-rate curve materially.
Email events@safeguard.sh to coordinate a meeting at any of the events above, or open contact to drop a general note.