Secure LLMs & Prompt Defense 2025

Secure LLMs & Prompt Defense 2025

Red-teaming, jailbreaks, isolation

Sep 15, 2025 2:00 AM — 10:30 AM San Jose Convention Center, 150 W San Carlos St • San Jose, CA, 95113, US Public Published USD 249.00 – 699.00 • Cap 1600
← All Events Register Event Website

Event Details

Summary: Prompt injection defense, isolation, policy.

Guardrails, content filters, eval harnesses, and isolation patterns.

When: Sep 15, 2025 2:00 AM — 10:30 AM (America/Los_Angeles)

Where: San Jose Convention Center, 150 W San Carlos St • San Jose, CA, 95113, US

Accessibility: Wheelchair access

Organizer: REGKT Events • events@regkt.org • +1-408-000-0000

Participants

Dr. Dr. Nina Volkov 🇺🇸

CinderSec

LLM Security Researcher

Keynote: Opening Keynote Track: Keynotes Room: Main Hall Sep 15, 2025 2:00 AM – 2:45 AM Featured

Keynote: Jailbreaks & Defenses: Lessons from LLM Red-Teaming

Isolation patterns, layered filters, continuous evaluation.

Focus on jailbreak defense and eval harnesses.

Prof. Prof. Mateo Alvarez 🇺🇸

UC Santa Clara

Professor of Secure NLP

Keynote: Day 2 Keynote Track: Keynotes Room: Main Hall Sep 16, 2025 2:00 AM – 2:45 AM Featured

Keynote: Beyond Prompt Injection: Supply-Chain Threats

Weights, datasets, tool plugs and provenance verification.

Security of language models and aligned systems.

Ava Jensen 🇺🇸

PromptShield

Head of Trust & Safety

Session_chair: Track A Chair Track: Track A Room: Room A Featured

Chair: Session

Runs incident response and abuse prevention for LLM apps.

Dr. Dr. Raghav Raman 🇺🇸

BenchAI

Staff Researcher, Eval Systems

Session_chair: Track B Chair Track: Track B Room: Room B Featured

Chair: Session

Designs adversarial evals for LLM safety.

Noah Patel 🇺🇸

TrustForge

Security PM

Workshop_instructor: Hands-on Workshop Track: Workshops Room: Room W1 Sep 16, 2025 3:30 AM – 5:00 AM Featured

Workshop: Writing Effective Guardrail Policies

Templates, exception queues, and staged rollout.

Policy rollouts and exception handling.

Eleanor Park 🇺🇸

ModelSafe

Security Engineer

Speaker Track: Track A Room: Room A Sep 15, 2025 4:00 AM – 4:30 AM

Talk: Multi-Agent Attack Surfaces

Coordination exploits and role confusion attacks.

Red-teaming pipelines for multi-agent systems.

Yusuf Karim 🇺🇸

GuardTrail

Principal Engineer

Speaker Track: Track A Room: Room A Sep 15, 2025 4:35 AM – 5:05 AM

Talk: Tool Use Isolation: Sandboxes that Scale

Syscall filtering, broker patterns, and escape prevention.

Runtime isolation and sandbox patterns for LLM tools.

Mira Kowalski 🇵🇱

TraceWorks

Data Provenance Lead

Speaker Track: Track B Room: Room B Sep 15, 2025 7:00 AM – 7:30 AM

Talk: Provenance-First Training Data

Hash chains, attestations, and human-in-the-loop QA.

Dataset lineage and tamper-evident curation.

Dr. Dr. Wei Chen 🇸🇬

SafeLang Labs

Research Scientist

Speaker Track: Track B Room: Room B Sep 15, 2025 7:35 AM – 8:05 AM

Talk: A Practical Taxonomy of Jailbreaks

Injection family tree with concrete mitigations.

Alignment evals and jailbreak taxonomy.

Sara M�ller 🇩🇪

BlueCanary

Incident Response Lead

Panelist: Panelist Track: Panels Room: Room P Sep 15, 2025 9:00 AM – 9:45 AM

Panel: Incident Postmortems that Actually Fix Things

Runbooks, decision logs, and accountability loops.

Runs post-mortems for LLM incidents.

Jacob Reed 🇺🇸

Independent

Moderator

Moderator: Panel Moderator Track: Panels Room: Room P Sep 15, 2025 9:00 AM – 9:45 AM

Panel: Incident Postmortems that Actually Fix Things

Moderating panel on disciplined remediation.

Moderator for security/AI panels.

Isabella Rossi 🇮🇹

EvalCraft

Eval Engineer

Speaker Track: Track C Room: Room C Sep 16, 2025 6:30 AM – 7:00 AM

Talk: From Static Benchmarks to Continuous Evals

Shift from one-off scores to live signals.

Builds eval harnesses and dashboards.

Dr. Dr. Omar Saad 🇦🇪

LLM Risk Lab

Research Lead

Speaker Track: Track C Room: Room C Sep 16, 2025 7:05 AM – 7:35 AM

Talk: Risk Registers that Matter

Severity scales and near-miss logging for AI incidents.

Risk registers and governance boards.

Emily Ward 🇺🇸

REGKT Events

Organizer

Organizer: Program Operations

Ops: Session

Program operations and speaker success.

Liam O'Connor 🇺🇸

REGKT Events

Organizer

Organizer: Logistics Lead

Ops: Session

Venue logistics and A/V.

Judith Park 🇺🇸

OpenEval

Judge

Judge: Poster Awards Judge Sep 16, 2025 8:30 AM – 9:30 AM

Judging: Session

External evaluator for poster awards.

Rafael Santos 🇧🇷

Citadel AI

Security Architect

Speaker Track: Track A Room: Room A Sep 16, 2025 8:00 AM – 8:30 AM

Talk: Broker Patterns for Toolformer-Style Agents

Decoupling tools with capability bounding.

Interfaces for safe tool use.

Chen Li 🇨🇳

PromptLab

Research Engineer

Panelist: Panelist Track: Panels Room: Room P Sep 16, 2025 9:45 AM – 10:30 AM

Panel: Measuring Safety: Where Benchmarks Fail

Panel on eval blind spots and proxy metrics.

Safety taxonomies and test corpora.

Sofia Dimitriou 🇬🇷

Independent

Moderator

Moderator: Panel Moderator Track: Panels Room: Room P Sep 16, 2025 9:45 AM – 10:30 AM

Panel: Measuring Safety: Where Benchmarks Fail

Moderates panel discussion on evals.

Moderator for policy/safety panels.

Diego Herrera 🇲🇽

ShieldWorks

Workshop Instructor

Workshop_instructor: Hands-on Lab Track: Workshops Room: Room W2 Sep 15, 2025 6:30 AM – 8:00 AM

Workshop: Implementing Policy as Code

OPA examples and deployment pipelines.

Policy templates and rollout strategies.

Professional Impact & Significance

This event represents a platform where leaders, researchers, and practitioners exchange advancements that influence real-world technical, scientific, and organizational practices. The contributions and presentations delivered here reflect recognized expertise in the field and demonstrate active participation in advancing modern knowledge.

Participants are encouraged to archive discussions, slide decks, and session recordings as part of documenting their contributions, outcomes, and role in shaping the dialogue presented here.

← Back to All Events Register