Best Talks at [un]prompted 2026 — AI Security Practitioner Conference

Hand-picked from in-depth reviewer verdicts — the top 12 talks from this conference. Skip the noise, find the signal.

← All talks at [un]prompted 2026 — AI Security Practitioner Conference

1

Black-hat LLMs

Nicholas Carlini

Nicholas Carlini, a research scientist at Anthropic and one of the most respected voices in AI security, delivered a talk that the conference organizer introduced as a "global-level emergency." Using minimal scaffolding — a single Claude command-line invocation — Carlini and…

0 Dr. Zero MUST SEE ★★★★★ H Heather Calloway MUST SEE ★★★★★
2

8 Minutes to Admin. We Caught It in the Wild. Welcome to VibeHacking

Sergej Epp

0 Dr. Zero MUST SEE ★★★★★ H Heather Calloway MUST SEE ★★★★★
3

Capability-Based Authorization for AI Agents: Warrants That Survive Prompt Injection

Niki Aimable Niyikiza

The authorization models enterprises built for microservices are fundamentally broken for AI agents. Niyikiza introduces the "Tenuo warrant" — a capability-based, cryptographically signed, task-scoped authorization primitive that freezes an agent's blast radius at delegation…

0 Dr. Zero MUST SEE ★★★★★ H Heather Calloway MUST SEE ★★★★★
4

Are Your LLM's Safety Mechanisms Intact? Detecting Backdoors with White-Box Analysis

Akash Mukherjee

Akash Mukherjee demonstrated live that a backdoored LLM is completely indistinguishable from a clean model under standard black-box testing — but detectable in seconds by monitoring internal neural activations. His argument: open-weight models are an unsolved supply chain…

0 Dr. Zero MUST SEE ★★★★★ H Heather Calloway MUST SEE ★★★★★
5

Evaluating Threats & Automating Defense: How Google is Advancing Code Security

Heather Adkins, Four Flynn

Google and Google DeepMind researchers presented two integrated AI projects — Big Sleep for autonomous vulnerability discovery and CodeMender for autonomous patch generation — with the explicit goal of eliminating every software vulnerability on Earth. Both systems achieve zero…

0 Dr. Zero MUST SEE ★★★★★ H Heather Calloway STRONG ACCEPT ★★★★☆
6

Guardrails beyond Vibes: Shipping Security Agents in Production

Jeffrey Zhang, Siddh Shah

Stripe's security engineering team replaced ad hoc "vibe checks" with a rigorous engineering discipline for deploying AI security agents in production. By combining modular multi-agent architectures with a golden-standard evaluation pipeline using LLM-as-judge, they shipped a…

0 Dr. Zero STRONG ACCEPT ★★★★☆ H Heather Calloway MUST SEE ★★★★★
7

When Passports Execute: Exploiting AI Driven KYC Pipelines

Sean Park

TrendAI principal threat researcher Sean Park demonstrated how stored prompt injection attacks embedded in passport images can cause AI-driven KYC (Know Your Customer) pipelines to exfiltrate other users' identity data. More importantly, he showed how to scale and automate the…

0 Dr. Zero STRONG ACCEPT ★★★★☆ H Heather Calloway MUST SEE ★★★★★
8

FENRIR: AI Hunting for AI Zero-Days at Scale

Peter Girnus, Derek Chen

TrendAI's Zero Day Initiative team built FENRIR, an AI-powered vulnerability discovery engine that combines traditional static analysis with a cascade of LLM triage stages to find zero-day bugs at scale. In production, FENRIR has delivered a 2.5x increase in vulnerabilities…

0 Dr. Zero MUST SEE ★★★★★ H Heather Calloway STRONG ACCEPT ★★★★☆
9

Vibe Check: Security Failures in AI-Assisted IDEs

Piotr Ryciak

Mindgard's AI red team discovered 37 vulnerabilities across more than 15 AI-assisted IDE vendors, including Google Gemini CLI, OpenAI Codex, and Amazon Q. The attack patterns fall into four categories — zero-click, one-click, autorun, and time-delayed — and many succeed even…

0 Dr. Zero STRONG ACCEPT ★★★★☆ H Heather Calloway MUST SEE ★★★★★
10

SIFT – FIND EVIL!! I Gave Claude Code R00t on the DFIR SIFT Workstation

Rob T. Lee

Rob Lee, creator of the SIFT Workstation, gave Claude Code root access on a DFIR forensics environment and told it to "find evil." The result: a full forensic analysis that previously took human analysts two to three days compressed to 14 minutes and 27 seconds, with 100%…

0 Dr. Zero STRONG ACCEPT ★★★★☆ H Heather Calloway MUST SEE ★★★★★
11

Can You See What Your AI Saw?: GenAI Endpoint Observability for Detection Engineers

Mika Ayenson

Your EDR sees a curl command. Was it your developer, or an AI agent manipulated by a poisoned README? Mika Ayenson of Elastic exposes the core crisis facing detection engineers in 2026: intent attribution is broken. With AI coding tools spawning shells, writing files, and…

0 Dr. Zero STRONG ACCEPT ★★★★☆ H Heather Calloway MUST SEE ★★★★★
12

Kinetic Risk: Securing and Governing Physical AI in the Wild

Padma Apparao

When AI moves from screens to the physical world, errors stop being recoverable — they become kinetic events measured in force, speed, and mass. Padma Apparao of Intel argues that physical AI requires an entirely different security and governance model, where latency is a…

0 Dr. Zero STRONG ACCEPT ★★★★☆ H Heather Calloway MUST SEE ★★★★★