Loading…

Subject: Threat Intel and DFIR clear filter
Saturday, September 12
 

10:30am CDT

AI-Assisted IR Without the Lies: A Browser Forensics Case Study
Saturday September 12, 2026 10:30am - 11:30am CDT
Offensive security teams are deploying autonomous agents that chain vulnerabilities end to end without human intervention. Vulnerability researchers are using LLMs to discover and exploit zero-days at a pace no human team can match. AI is already on both sides of the fight, and the gap between organizations that harness it and those that do not is widening fast.
Incident responders have largely held back, and for a good reason.
In IR, a hallucination is not a minor inconvenience. A fabricated timeline entry, a missed lateral movement path, or a confidently wrong attribution can mean a backdoor stays in the network, exfiltrated data goes unaccounted for, or an organization remediates a fiction while the real compromise remains intact. The stakes are not just technical. IR findings increasingly inform legal proceedings, regulatory responses, and executive decisions. Forensic evidence analyzed by a system that invents facts has no place in that chain.
And yet: if AI can genuinely accelerate triage and scope analysis, the organizations we respond for recover faster. That matters.
In the past months, we have been solving the precision problem rather than avoiding it. We started with one concrete use case: browser forensics. Using a combination of skills and agents, we built a pipeline that accelerates artifact triage and timeline reconstruction on real engagements.
The pipeline fetches browser history directly from the endpoint regardless of OS, parses artifacts across Chrome and Edge, and searches for relevant entries based on the suspicious activity that prompted the investigation, whether that is a domain, a time window, or a combination of both. What previously required an analyst to manually locate, extract, and cross-reference browser databases is now scoped and surfaced automatically, with the agent linking findings back to the original investigation context.
In this talk, we walk through exactly how we built it, how we validated the outputs, where the model failed, and what we put in place to catch it. We will also share what we learned and how we plan to apply those lessons to other elements of IR going forward.
Attendees will leave with a clear picture of how to structure a skills and agents pipeline for forensic analysis, the specific validation techniques we used to constrain hallucinations, and a realistic sense of where AI-assisted IR is ready for production and where it is not.
Speakers
avatar for Kyle Henson

Kyle Henson

Security Engineering Team Leader, Daylight Security
Kyle is an incident response leader with more than seven years of experience in DFIR and threat intelligence. He is currently a Security Engineering Team Lead at Daylight, where he builds agentic security services such as MDR, threat hunting, and incident response that combine automated... Read More →
avatar for Aaron Hau

Aaron Hau

Security Engineering Team Leader, Daylight Security
Aaron is a security researcher with more than five years of experience across various aspects of Cybersecurity including Incident Response, Red Teaming and Security Research. He is currently a Security Engineering Team Lead at Daylight, where he builds agentic security services such... Read More →
Saturday September 12, 2026 10:30am - 11:30am CDT
Swissôtel Chicago 323 E Wacker Dr, Chicago, IL 60601, USA
  Talk

10:30am CDT

From Hours to Minutes With StealerLens: LLM-Accelerated Infostealer IR for Overwhelmed SOCs
Saturday September 12, 2026 10:30am - 11:30am CDT
Information stealer malware has quietly become one of the most consequential threats facing modern SOCs, with over 50 million stealer logs posted on underground channels in the last year alone. Each log is a comprehensive digital dossier on a single victim, and the sheer volume has created an analysis bottleneck that is impossible to address at scale.
This session opens with a technical deep dive into what an infostealer actually is and the strange artifact that is a stealer log. Beyond the obvious credentials and session cookies, stealer logs contain things defenders rarely expect: browser password manager extension data (BitWarden, Dashlane, KeePassXC), local KeePass vaults exfiltrated from disk, TOTP secrets leaked from Chrome extensions bypassing MFA, cryptocurrency wallet data, personal documents, and desktop screenshots captured at the exact moment of compromise. We will walk through the full attack surface and show why modern stealers are far more dangerous than "just a credential dump".
Buried inside each log are also forensic breadcrumbs left by the malware itself: execution paths, active processes, installed software, browser history, clipboard contents. These artifacts can reconstruct the infection vector and reveal the malware's behavior, but analyzing them manually takes hours per log. For an overwhelmed SOC triaging a steady stream of incidents, this analysis simply does not happen.
Building on our BlackHat USA 2025 work on LLM-based infection screenshot analysis ("Hackers Dropping Mid-Heist Selfies"), we introduce StealerLens, an LLM-powered forensic tool that collapses this workflow from hours to minutes. StealerLens uses a layered architecture where each log artifact (system info, software inventory, processes, browser history, clipboard, screenshots) is analyzed by a dedicated prompt. A final master prompt correlates the outputs into a cohesive infection narrative: likely source of infection, delivery vector, blast radius of exposed information, and pointing to the supporting evidence so the analyst can verify at a glance.
We will share the full prompt architecture, walk through real anonymized cases, discuss the limits we encountered across our test corpus. Attendees leave with a concrete blueprint for industrializing infostealer log analysis — and making room for the strategic work their SOC actually needs to do.
Speakers
avatar for Olivier Bilodeau

Olivier Bilodeau

Principal Cybersecurity Researcher, Flare
Olivier Bilodeau, a principal researcher at Flare, brings 15+ years of cutting-edge infosec expertise in honeypot operations, binary reverse-engineering, RDP interception and, more recently, fighting information stealer malware. Passionate communicator, Olivier spoke at conferences... Read More →
Saturday September 12, 2026 10:30am - 11:30am CDT
Swissôtel Chicago 323 E Wacker Dr, Chicago, IL 60601, USA
  Talk

10:30am CDT

It Started with an Employee. It Ended Inside Your AI: The Exposure Chain You Need to Understand
Saturday September 12, 2026 10:30am - 11:30am CDT
AI didn't just speed up reconnaissance. It connected dots that were never supposed to connect and most blue teams haven't caught up yet.
 
This talk walks through a single, end-to-end exposure chain so defenders can finally see what they're up against, and know exactly where to break it.
It starts with people. AI-powered OSINT pipelines aggregate and correlate employee data across LinkedIn, GitHub, forums, and breach databases in minutes, building behavioral profiles precise enough to generate hyper-targeted phishing lures at scale. But the exposure doesn't stop at individuals. The same reconnaissance that maps employees also maps the company: infrastructure, misconfigured services, and increasingly API endpoints leaked during LLM deployments. Production AI tools calling internal services, chatbots inadvertently surfacing internal documentation, LLM APIs left exposed during staging, these aren't edge cases, they're patterns blue teams are consistently missing.
 
From there, the path in is shorter than most teams think. Either a well-profiled employee gets phished into opening the door, or an exposed AI-connected service was never meant to be public in the first place. And once an attacker reaches an internal LLM: a security chatbot, an AI-assisted SIEM, an LLM-integrated IR tool, prompt injection becomes the final piece. Your AI doesn't know the difference between a legitimate query and a crafted instruction. Your analyst might not either.
 
We'll demonstrate each stage, then flip the lens entirely covering how defenders can map their AI exposure, harden LLM-integrated tooling, and break the chain before it completes.
 
Attendees will leave with:
  • Visibility into how AI-powered recon pivots from employees to exposed infrastructure
  • Awareness of LLM deployment patterns that unintentionally surface internal services
  • A framework for identifying prompt injection risks in security tooling
  • Actionable steps to audit and defend their AI attack surface
Speakers
avatar for Derick Johnson

Derick Johnson

Derick Johnson is a cybersecurity graduate student and practitioner specializing in the intersection of AI, large language models, and offensive security. His research focuses on two converging threats: how AI-powered tools are transforming open-source intelligence and reconnaissance... Read More →
Saturday September 12, 2026 10:30am - 11:30am CDT
Swissôtel Chicago 323 E Wacker Dr, Chicago, IL 60601, USA
  Talk

10:30am CDT

It Wasn’t Spoofed: Investigating Authenticated Email Abuse in Real Environments
Saturday September 12, 2026 10:30am - 11:30am CDT
Not every incident starts with an alert.

Sometimes it starts with a confident assumption.

In this case, a suspicious email spread internally. The user reported they did not send it, and the client confidently assessed the message as spoofing.

It wasn’t.

Email header analysis revealed the message originated from within the organization (AuthAs: Internal) using legacy SMTP AUTH (AuthMechanism: 04), an authentication pathway that does not enforce MFA. Valid credentials were used, no alerts were generated, and the activity appeared legitimate.

With limited visibility, the investigation required correlating endpoint and infrastructure telemetry. Pivoting on domains associated with file retrieval revealed additional impacted systems beyond those initially reported.

The incident exposed gaps in both detection and control coverage. Mailbox forwarding rules enabled data exfiltration and were managed reactively rather than preventively, while authentication-based detection failed due to legitimate credential use. When questions arose around credential origin, validation had to be guided within the client’s own environment while maintaining privacy and access boundaries.

This talk provides practical guidance for defenders, including how to:
  • distinguish spoofed emails from authenticated internal activity using header analysis
  • identify authentication pathways where MFA is not enforced
  • pivot on DNS and endpoint telemetry to expand incident scope
  • detect and reduce risk from mailbox forwarding rules
  • validate potential credential exposure within appropriate privacy and access boundaries
  • investigate effectively when activity appears legitimate and generates no alerts
Attendees will leave with practical approaches for identifying and responding to attacks that bypass traditional detection by blending into expected behavior.
Speakers
avatar for Kelsey O'Connell, w0mbat

Kelsey O'Connell, w0mbat

Tier II MDR Analyst, Beazley Security
Kelsey (w0mbat) is a cybersecurity analyst focused on detection, investigation, and response, with an emphasis on cases where activity appears legitimate but is not. Her work spans endpoint, identity, and email telemetry, specializing in identifying subtle indicators of compromise... Read More →
Saturday September 12, 2026 10:30am - 11:30am CDT
Swissôtel Chicago 323 E Wacker Dr, Chicago, IL 60601, USA
  Talk

10:30am CDT

Teaching AI to Analyze Malware: How to Encode Practitioner Expertise into an MCP Server
Saturday September 12, 2026 10:30am - 11:30am CDT
AI agents can reason about suspicious files, plan multi-step investigations, and write custom deobfuscation code when standard tools fall short. But generic models produce shallow, unreliable results because they lack practitioner knowledge about which tools to use and when, and access to the tools themselves.
Without domain expertise, an AI agent doesn't know that, for example, capa exit codes follow non-standard conventions, that YARA match counts require context to interpret, or that GetProcAddress appears in virtually every Windows program and is not inherently suspicious. Without tool access, it can only comment on malware but cannot investigate it.
This talk walks through my experience of building an open source MCP server, a standardized interface that connects AI agents to external tools, that bridges both gaps simultaneously. The server connects AI agents to my open source REMnux malware analysis toolkit, encoding practitioner knowledge into tool workflow sequencing and output interpretation. The server runs analysis at three depth levels, and manages context budgets when tool output exceeds approximately reasonable values by automatically switching to summary mode while preserving key findings.
The server also counteracts confirmation bias. Generic AI agents tend to label every API call as suspicious and every string as an indicator of compromise. The server's neutral framing prompts agents to consider benign explanations before concluding malicious intent. This is a critical safeguard when the AI chains dozens of tool calls without human review at each step.
Against real-world samples, the resulting system completed full investigations in about 10 minutes with 25-30 automated tool calls. In one case during my experimentation, the AI agent wrote custom Python to reconstruct a PE from file fragments. In another, it reverse-engineered a proprietary archive format and adapted when initial analysis approaches failed.
The talk covers what worked, what failed, and what surprised me. It addresses the security model required when AI agents have tool access, including prompt injection risks from malicious content in analyzed samples, container isolation as the primary security boundary, and data flow considerations.
Attendees leave with a reproducible pattern for encoding domain expertise into MCP servers, applicable to incident response, cloud forensics, network analysis, or any domain with specialized tools and practitioner workflows.
Speakers
avatar for Lenny Zeltser

Lenny Zeltser

Faculty Fellow, SANS Institute
Lenny Zeltser is a cybersecurity executive with deep technical roots, product management experience, and a business mindset. He has built security products and programs from early stage to enterprise scale. He is also a Faculty Fellow at SANS Institute and the creator of REMnux, a... Read More →
Saturday September 12, 2026 10:30am - 11:30am CDT
Swissôtel Chicago 323 E Wacker Dr, Chicago, IL 60601, USA
  Talk

10:30am CDT

The Malware Is Coming from Inside the Repo
Saturday September 12, 2026 10:30am - 11:30am CDT
GitHub isn't just where developers work. It's where adversaries stage, obfuscate, and deliver malicious code. Every minute, thousands of commits hit public repositories, and buried inside that firehose are credential stealers, reverse shells, crypto drainers, and the occasional nation-state lure dressed up as a coding challenge. The platform's openness, trust, and sheer volume are exactly what make it useful to attackers: free hosting, free CDN, a developer-friendly domain in every allowlist, and a culture where running npm install or cloning a stranger's repo is just Tuesday.

This talk is about what happens when you actually try to watch all of it.

We'll walk through github-threat-scanner, a pipeline that consumes the GitHub public event stream in near real time, pulls down the code behind every push, and runs it through a stack of decoders and detection rules looking for anything that smells wrong. The interesting problems aren't where you'd expect. Ingesting the stream is easy. Storing it is a solved problem. The hard parts are everything in between: peeling back the layers of obfuscation attackers use to hide payloads, deciding what "malicious" even means when half the internet's legitimate code looks suspicious, and keeping false positives low enough that a human analyst can still trust the queue.

We'll dig into the deobfuscation engine (CyberSaucier), a library of CyberChef recipes that chain together XOR bruteforcing, base64 and hex decoding, packed-JavaScript unwrapping, PowerShell de-munging, and the other tricks that turn a wall of gibberish back into something a detection rule can match on. You'll see which recipes earn their keep, which ones we retired because they were pure theatre, and the surprisingly mundane reasons some decoders fail in production that never show up in a blog post.

Then we'll get to the fun part: who's actually out there. Commodity and Nation State actors treat GitHub Pages as disposable infrastructure. And threading through all of it are the targeted operations: DPRK-aligned clusters running fake job interviews and "technical assessments" that ship trojanized projects to developers at crypto firms and long-running personas that maintain plausible commit histories for months before turning hostile.

You'll leave with a concrete picture of how to build this kind of visibility yourself, what the detection surface actually looks like once you're watching it, and why GitHub deserves a seat in your threat model next to email and the browser. If you run a security team, you'll walk out with questions to take back to your developers. If you write detections, you'll have new ideas for where to point them. And if you just like watching adversaries do dumb things at scale, there will be plenty of that too.


The best part of all of this? Most of this data was initially triaged and analyzed by an autonomous AI analyst running in a throwaway VM in dangerous mode, unafraid of touching actual adversary infrastructure.

No prior knowledge of GitHub internals required. Bring opinions about regex.
Speakers
avatar for Justin Borland

Justin Borland

Director of Threat Engineering, Abstract
A proven technical leader in the security industry, Justin started his career with a Canadian Secret clearance while still in College. After graduating, he spent the next decade building custom packet capture systems, intrusion detection systems, logging systems, and DFIR tooling... Read More →
Saturday September 12, 2026 10:30am - 11:30am CDT
Swissôtel Chicago 323 E Wacker Dr, Chicago, IL 60601, USA
  Talk

10:30am CDT

Threat Intelligence at the Speed of Cyber Defense
Saturday September 12, 2026 10:30am - 11:30am CDT
Cyber threat intelligence (CTI) is essentially a decision support function within cybersecurity. As such, CTI that cannot enable, improve, or otherwise facilitate a security action is of questionable value. This is often evaluated in terms of CTI relevance, applicability, or accuracy, but the relationship between CTI and security actions also demands investigation of another metric: timeliness. CTI that arrives too late for the supported decisions is functionally irrelevant.


In this discussion we will explore the implications of a time-oriented view for CTI production, dissemination, and integration into operationally-focused decision making. From this we will identify a key tension at the core of CTI analysis and production: that the SPEED at which CTI is produced and disseminated is often in conflict with the QUALITY or DEPTH of the produced CTI. Organizations cannot have immediate decision support on tactically-relevant timescales while simultaneously having deep context in the current environment. As a result, tradeoffs are necessary to both recognize and navigate in developing a relevant CTI function. Furthermore, evaluating CTI becomes a question of determining audience and customer needs, purpose, and response timelines to appropriately structure CTI support for the entity or specific decision maker in question.


To conclude this discussion, we will examine the possibility of eliminating (or at least reducing) this dilemma through technical means. Particularly future progress in the field of artificial intelligence may allow CTI functions to tap into mechanisms where context or detail and timeliness are no longer in direct conflict with one another, mapping out an effective and meaningful way for AI to support CTI and broader security functions.
Speakers
avatar for Joe Slowik

Joe Slowik

Director, Cybersecurity Alerting Strategy, Dataminr
Joe Slowik has over 15 years of experience across multiple cyber domains, from threat intelligence to detection engineering to incident response. Joe currently works as director for cyber alerting strategy at Dataminr, and has previously held roles at organizations including the MITRE... Read More →
Saturday September 12, 2026 10:30am - 11:30am CDT
Swissôtel Chicago 323 E Wacker Dr, Chicago, IL 60601, USA
  Talk
 
Blue Team Con 2026
From $0.00
Share Modal

Share this link via

Or copy link

Filter sessions
Apply filters to sessions.