DevSecOps - London Gathering

## Details

Welcome to the DevSecOps London Gathering July Event on Wednesday 22 July! We bring you speakers, as well as the usual conversations, pizza and beer!

📍 Hosted at Civo Tech Junction, 1st Floor, 32-37 Cowper Street, London, EC2A 4AW
📅 Wednesday, 22 July
🕕 6:00–8:00 PM

## Talk Abstracts:

Lightning Talk - Using AI prompts for disaster recovery - by John Davies
After Zafrul Sattar's talk at the end of 2025, he gave out to those who asked the prompt he had demonstrated. This lightning talk will demonstrate a development of Zafrul's prompt that drafts disaster recovery plans. The talk will describe what changed and why, what worked
and didn't and what might be done next.
John's Bio:
John is an accountant with ingrowing computers. He started punching cards for fun in 1974 and has more accounting qualifications than anyone
could possibly need. An unrepentant bookworm, he still has Pascal and
COBOL manuals from the 1970s which he has been known to quote in answer to Perl problems in 2017. He yearns for the "good old days" when
documentation came in glossy manuals and didn't make him rant. His pipe
dream is for software that doesn't make him rant. Or even for accounting
laws and standards that don't.
Main Talk - How hackers are targeting deployment path developers by David Read and Valentino Duval
DevSecOps has spent years hardening CI/CD, but recent campaigns show that the developer is now part of the deployment path attackers are targeting. In this talk, we will walk through what Ossprey found while tracking real supply chain activity, including DPRK interview lures, second stage malware, credential theft, poisoned developer tools, malicious packages and AI assisted code compromise. Rather than treating these as isolated incidents, we will show the patterns that linked them together: reused infrastructure, obfuscation choices, token flows, package behaviour and attacker tradecraft across npm, PyPI, and GitHub. The focus is technical and investigative: what we saw, how we connected it, what surprised us, and what defenders can realistically monitor.
David's Bio:
David has over 16 years of experience working in cyber security working as a researcher, architect and security engineering manager. Recently David cofounded Ossprey a cyber security company that specialises in detecting and stopping open source malware attacks.
Valentino's Bio:
Valentino is an engineer and security researcher at Ossprey, working on the front lines of open source malware detection. He specialises in uncovering, analysing and disrupting malicious campaigns targeting developers, packages and the wider software supply chain.

## Details

Welcome to the DevSecOps London Gathering March Event on Wednesday 16 September. Along with our amazing talks we bring you the usual conversations, pizza and beer! And because this is our anniversary event, there may be cake!!

Location:

• 📍 Venue: Civo Tech Junction, 1st Floor, 32-37 Cowper Street, London, EC2A 4AW
• 📅 Date: Wednesday, 16 September 2026
• 🕕 Time: 6:00 PM – 8:00 PM

## Talk 1 - Darshan Patil - Poisoning the training ground

Abstract:
As more teams shift toward AI-native workflows, we're adding ML models to the delivery pipeline. Label flipping attacks are a silent data supply-chain threat—they corrupt training labels, degrade model performance, and traditional AppSec tooling misses them entirely.

I want to walk the audience through:
- What label flipping looks like (attack demo in PyTorch)
- Discuss Defenses
- Detecting label flipping, baking in defense etc.

It's hands-on, practical, and designed around "what can I implement Monday morning"—not pure theory.

I'm a practitioner, not a vendor—just sharing what we're learning in the trenches at a fintech company dealing with these exact concerns.
Speaker Bio:
Darshan is an application security engineer with a software development background, specialising in integrating security throughout the SDLC. Experienced in SAST, DAST, IAST, and SCA tools including Burp Suite, OWASP ZAP, Semgrep, GitHub Advanced Security, and SonarQube. Skilled in threat modeling, secure code reviews, penetration testing, API security, DevSecOps, and cloud security across AWS, Azure, and GCP. Focused on security automation with Python and Go, CI/CD security, and developer enablement. Experienced in securing AI applications on AWS Bedrock, implementing guardrails, and testing for prompt injection and jailbreak vulnerabilities aligned with OWASP LLM guidance. Passionate about mentoring, security advocacy, and driving impactful security initiatives..

## Talk 2 - Sunny Chau - The Agent's inner monologue

Abstract
Most agent defenses sit at the edges - input filters, output classifiers, hardened system prompts. Nobody is watching what the agent is actually thinking. And the attack surface that creates is real: indirect prompt injection, tool poisoning, reasoning trace manipulation, exfiltration dressed as legitimate tool use.
Recent research from OpenAI and DeepMind found that monitoring an agent's chain of thought improves attack detection by 35% and is 4x more likely to catch nuanced compromise than action-level monitoring alone.
Drawing on seven years in offensive security and red team leadership, I'll walk through live attacks against production agents and show how Adrian, Secure Agentics' open-source runtime monitor, catches and stops each one by watching the inner monologue — not just the output.
Speaker Bio:
Sunny has 4 years of offensive cyber security experience working as a penetration tester and a covert red teamer, having spoken at various security conferences around the world including BSides London, Athens, Hong Kong, Beac0n and more on cloud-native security, identity hacking and all that good stuff. He took his adversarial mind to Secure Agentics as Head of Research, where he leads work on the agentic attack surface, finding the ways autonomous agents get compromised in production, and building the detection logic to catch it.