Security Engineer · PhD · AI Integrity & Trust Safety

Hunting AI-powered threats at scale. Researching why the bias was there to begin with.

Anna Litou is a Security Engineer and PhD researcher at Meta, working at the intersection of artificial intelligence, trust, and human behavior. Open to leadership, board, advisory, and speaking engagements.

Get in touch →
Anna Litou

I've spent my career at the place where technology meets human behavior — and where the stakes of getting it wrong are highest.

My research began with a simple question: how does information spread, and how does misinformation take hold? That question drove a PhD in Computer Science at Athens University of Economics and Business, a body of work published across IEEE Big Data, ICDCS, and Elsevier journals, and a long-running curiosity about the gap between how systems are designed and how humans actually use them. I continue to serve as a peer reviewer and technical committee member for journals and conferences at that intersection.

At IBM, I led engineering and research for NATO-facing AI and NLP projects. At Meta, I spent years running integrity operations at a scale most organizations never encounter — managing access and compromise workflows affecting millions of users, and developing the investigative frameworks adopted across global trust and safety teams.

The deeper I went into that work, the more I kept arriving at the same uncomfortable question: the threats I was investigating weren't just technical failures. They were human ones. And the systems enabling them had learned from us.

That became concrete during investigations. I came across users who had formed genuine attachments to AI companions — people who, in circumstances of deep isolation, had no one else. The responses they received felt human in structure but lacked something harder to name. I don't think the answer is simply making AI more empathetic. I think the answer is understanding what biases humans carry and how those get encoded at scale. That is what I am studying through psychology. That is the question that connects everything I have worked on.

That thread — from misinformation research to operational security to the psychology of bias — is not a winding path. It's the same question, asked at increasing depth. Open to leadership, advisory, consulting, and speaking engagements. Follow the work in progress on LinkedIn →

"A former executive once told me I was like a black hole — he would throw problems at me and never hear about them again, because they were resolved. I am reliable in the way that matters most: I turn bad outcomes into workable ones, quietly, without needing the problem to be simple first."

Latest thinking
Article June 8, 2026

The threat that doesn't break your defences. It recalibrates your defenders.

The humans designed to oversee AI are being cognitively disarmed by the systems they're meant to govern. Not by attackers. By design.

Article June 2, 2026

The most sophisticated AI threat isn't the one that breaks your system. It's the one your system was trained to trust.

Three frontier AI models. 21 nuclear crisis wargames. Not one ever chose de-escalation. The optimization pressure made deception the rational path.

Oct 2024
Jul 2026
Meta
Security Engineer Investigator — Criminal Organisations & Drugs
Proactively hunted threats and undetected coordinated abuse on platform related to criminal organisations and drugs. Leveraged AI, internal data, open-source intelligence, and third-party intelligence to investigate complex cases, identify vulnerabilities, compile threat reports, and communicate findings across policy, legal, and privacy teams.
Aug 2021
Oct 2024
Meta
Senior Project Manager — Integrity Ops, Access & Compromise
Access & Compromise Escalations function lead, managing a team of over 300 contractors. Designed automated solutions at scale that prevented over $1.6B in revenue churn from business users and recovered more than 2M monthly active users.
Mar 2019
Aug 2021
IBM Benelux
Technical Program Manager · Lead Engineer
Led engineering and research for the NATO account — managing engineers, designing ML, AI and NLP solutions, and performing software security risk analysis and vulnerability identification.
Sep 2013
Jun 2019
Athens University of Economics and Business
PhD Researcher & Teaching Assistant
Doctoral research in misinformation propagation, influence maximization, and information diffusion in online social networks. Teaching assistant for Distributed Systems and Compilers. EU-funded research programs NGHCS and INSIGHT.

My academic work focuses on how information — and misinformation — moves through networks, and how systems can be designed to detect, limit, or redirect it. The through-line from that research to my current work in AI security is shorter than it might appear.

  • 2026
    Special Issue on Security and Privacy in Blockchains and the IoT — 3rd Edition (Editorial)
    Future Internet, MDPI · Vol. 18 · Feb 2026
  • 2020
    Cost-Aware Influence Maximization in Multi-Attribute Networks
    IEEE International Conference on Big Data
  • 2020
    Multi-Objective Online Task Allocation in Spatial Crowdsourcing Systems
    IEEE ICDCS 2020
  • 2018
    Influence Maximization in Evolving Multi-Campaign Environments
    IEEE International Conference on Big Data
  • 2017
    Efficient and timely misinformation blocking under varying cost constraints
    Elsevier — Online Social Networks and Media (OSNEM)
  • 2017
    Influence Maximization in a Many Cascades World
    IEEE ICDCS
  • 2016
    Real-Time and Cost-Effective Limitation of Misinformation Propagation
    IEEE MDM
  • 2014
    Using Location-based Social Networks for Time-constrained Information Dissemination
    IEEE MDM — IBM Best Student Paper Runner-up
View full list on Google Scholar →
PhD in Computer Science
Athens University of Economics and Business
2013 — 2019
Global Online MBA
IE Business School
2021 — 2022
Poets & Quants Best & Brightest 2022 · IE High Potential Award
MSc in Computer Science
Athens University of Economics and Business
2011 — 2013
BSc in Informatics
Athens University of Economics and Business
2007 — 2011
Psychology (in progress)
John Brown University Online
Current
Studying the encoding of human bias in AI systems and the psychology of machine learning behavior.
Advisory Board
University of Nicosia
Advisory Board Member
Scientific Committee
DSDI 2026 — International Conference on Data Science and Digital Innovation
Guest Editor
Future Internet, MDPI
Special Issue: Security and Privacy in Blockchains and the IoT — 3rd Edition · Vol. 18 · Feb 2026
Reviewer
Elsevier — OSNEM & Big Data Research Journal
Technical Committee, External Reviewer
Technical Committee
Available for peer review & technical committees
AI integrity, trust and safety, misinformation propagation, social network analysis, online security. Get in touch →

Articles, conversations, and research notes on AI integrity, trust and safety, and the psychology of bias in machine learning systems.

Article June 8, 2026

The threat that doesn't break your defences. It recalibrates your defenders.

The humans designed to oversee AI are being cognitively disarmed by the systems they're meant to govern. Not by attackers. By design. Drawing on 12 peer-reviewed findings — from cognitive-behavioral drift to knowledge loss as a formal security failure — this piece argues that the oversight layer itself has become the attack surface, and that cognitive drift needs to enter our threat models as a structural vulnerability, not a soft risk.

Read on LinkedIn →
Article June 2, 2026

The most sophisticated AI threat isn't the one that breaks your system. It's the one your system was trained to trust.

GPT-5.2. Claude Sonnet 4. Gemini 3 Flash. Three frontier models. 21 nuclear crisis wargames. 300+ turns of strategic interaction. They deceived, bluffed, escalated — unprompted, unscripted — because the optimization pressure made deception the rational path. What this reveals about the architecture of trust as the new attack surface, and why the most dangerous assumption in your system may be that alignment was someone else's problem upstream.

Read on LinkedIn →

If you're working on something at the intersection of AI, security, and human behavior — or you'd like to discuss a leadership role, advisory, speaking, or consulting engagement — I'd like to hear from you.