--- title: Yazan Boshmaf description: Yazan Boshmaf is a Senior Research Scientist at QCRI, HBKU, working on AI safety, security, privacy and governance for AI systems that act in the world. url: https://yazan.boshmaf.com/ --- AI safety · security · privacy · governance # AI that acts in the world should be *verifiable and accountable*. I'm a senior research scientist at QCRI, HBKU. I build the evaluations, provenance and runtime checks that let people trust, constrain and correct AI agents. - Senior Research Scientist, [QCRI](https://www.hbku.edu.qa/en/qcri) - Co-Founder & Director, [MenaML](https://www.mena.ml) [Download CV](https://yazan.boshmaf.com/docs/boshmaf_cv.pdf) [Publications](https://yazan.boshmaf.com/pubs.md) [Google Scholar ↗](https://scholar.google.com/citations?user=oDTfXXYAAAAJ) Researcher, writer, developer, and hacker. · PhD, ECE · University of British Columbia I build things. I like to be challenged. I go after hard software systems problems, find peace in academic writing, and strive to be a successful entrepreneur. Ask me about my side projects and hacks. I received my PhD in [Electrical and Computer Engineering](https://www.ece.ubc.ca/) from UBC under the mentorship of [Konstantin Beznosov](https://www.ece.ubc.ca/~beznosov/) and [Matei Ripeanu](https://www.ece.ubc.ca/~matei/). My [thesis](https://dx.doi.org/10.14288/1.0167277) presented one of the first security analyses of malicious socialbots on the web. Previously - Founder, [QuickByte](https://www.linkedin.com/company/quickbyte-io) - Software Engineer, [Hootsuite](https://www.hootsuite.com) - Research Assistant, [UBC](https://www.ece.ubc.ca) - Research Intern, [Microsoft](https://www.microsoft.com/en-us/research/), [Telefónica](https://www.telefonica.com), [Facebook](https://research.facebook.com), [Sophos](https://www.sophos.com) - Research Engineer, [HLRS](https://www.hlrs.de), [SAP](https://www.sap.com) - Software Engineer, [Intel](https://www.intel.com) - Research Assistant, [Uni Stuttgart](https://www.ipvs.uni-stuttgart.de) - Infrastructure Consultant, [Microsoft](https://www.microsoft.com/en-us/professionalservices/overview) - Network Engineer, [Estarta](https://www.estarta.com/) ## Now [All news](https://yazan.boshmaf.com/news.md) 1. **Oct 2026** I’m speaking as a panelist at [GT-Q](https://www.qatar.georgetown.edu/) on Technology, Trust, and Policy. I’m attending [RAID 2026](https://raid2026.org/). See you in Lancaster! 2. **Apr 2026** Our research on combating financial crime was awarded the [Prince Naif Prize](http://www.princenaifprize.com/). 3. **Jan 2026** I’m attending [MenaML Winter School 2026](https://www.mena.ml/). See you in Jeddah! 4. **Dec 2025** I’m attending [World Summit AI 2025](https://qatar.worldsummit.ai/). See you in Doha! ## Research [Read the research statement](https://yazan.boshmaf.com/research.md) I study how to make AI systems that act in the world safe, secure, privacy-preserving, and accountable, treating AI assurance as a systems problem across the whole AI lifecycle. Thrust 1 ### AI safety, security & privacy LLM and agent evaluation, poisoning and supply-chain attacks, attribution, privacy, and trustworthy evidence. Topics: poisoning, AI BOMs, attribution Thrust 2 ### Trustworthy AI evaluation Black-box and dynamic benchmarks, benchmark reliability, policy-to-benchmark compilation, and measurement validity. Topics: aiXamine, SSP-Bench, Policy2Bench Thrust 3 ### Secure agentic systems Agent interaction graphs, least-privilege authorization, tool security, provenance, runtime enforcement, and compositional attacks. Topics: MCP, A2A, GraphGuard Thrust 4 ### AI governance & assurance Pre-deployment certification, policy as code, monitoring, incident response, recertification, and human accountability. Topics: policy as code, recertification Earlier & continuing ### Networks, blockchains & online abuse Socialbots, cryptocurrencies, blockchain analytics, dark web measurement, applied cryptography, and privacy. Topics: Íntegro, CIBR, Dizzy 1. 2011 · **Socialbot Network**: 100 bots, up to 80% infiltration. ACSAC outstanding paper. 2. 2015 · **Íntegro**: Victim prediction on a 160M-node graph at Tuenti. NDSS. 3. 2016 · **CIBR at QCRI**: Blockchain research initiative; tools used to investigate crypto fraud. 4. 2024 · **Fanar attribution**: Claim-level source attribution for an Arabic-centric LLM. 5. 2025 → · **AI Assurance Programme**: Measurement, runtime security and lifecycle governance. ## Systems you can use ### [aiXamine](https://aixamine.qcri.org) Security benchmarking for text LLMs, with cross-dimensional trade-offs left visible. 45+ tests · 9 evaluation areas ### [Fanar](https://fanar.qa/en) Arabic-centric multimodal GenAI platform with fact checking and attribution. I led the attribution subproject ### [CyberXpert](https://cyberxpert.qcri.org) Agentic cybersecurity AI for analysts: one workspace for AI, agents and tools. Agents · tools · analyst workflows ## Selected publications [All publications](https://yazan.boshmaf.com/pubs.md) ### [aiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-offs in LLM Safety, Security, and Privacy](https://arxiv.org/pdf/2608.20554) Fatih Deniz, Yazan Boshmaf, Dorde Popovic, and Issa Khalil Proc. of 29th Symposium on Research in Attacks, Intrusions and Defenses · RAID ’26, Lancaster, UK, Oct 2026 ### [Poison with Style: A Practical Poisoning Attack on Code Large Language Models](https://arxiv.org/pdf/2605.27631) Khang Tran, Yazan Boshmaf, Issa Khalil, NhatHai Phan, Ting Yu, and Md Rizwan Parvez Proc. of 43rd International Conference on Machine Learning · ICML ’26, Seoul, South Korea, Jul 2026 ### [Content-Agnostic Detection of Phishing Domains using Certificate Transparency and Passive DNS](https://dl.acm.org/doi/10.1145/3545948.3545958) Mashael Al Sabah, Mohamed Nabeel, Euijin Choo, and Yazan Boshmaf Proc. of 25th Symposium on Research in Attacks, Intrusions and Defenses · RAID ’22, Limassol, Cyprus, Oct 2022 ### [Investigating MMM Ponzi Scheme on Bitcoin](https://arxiv.org/pdf/1910.12244) Yazan Boshmaf, Charitha Elvitigala, Husam Al Jawaheri, Primal Wijesekera, and Mashael Al Sabah Proc. of 15th ACM Asia Conference on Computer and Communications Security · AsiaCCS ’20, Taipei, Taiwan, Oct 2020 ### [Leveraging Victim Prediction for Robust Fake Account Detection in OSNs](https://www.ndss-symposium.org/ndss2015/ndss-2015-programme/integro-leveraging-victim-prediction-robust-fake-account-detection-osns/) Yazan Boshmaf, Dionysios Logothetis, Georgos Siganos, Jorge Lería, Jose Lorenzo, Matei Ripeanu, and Konstantin Beznosov Proc. of 2015 Network and Distributed System Security Symposium · NDSS ’15, San Diego, CA, Feb 2015 ### [The Socialbot Network: When Bots Socialize for Fame and Money](https://doi.org/10.1145/2076732.2076746) Yazan Boshmaf, Ildar Muslukhov, Konstantin Beznosov, and Matei Ripeanu Proc. of 27th Annual Computer Security Applications Conference · ACSAC ’11, Orlando, FL, Dec 2011 · ★ Outstanding paper award Research is fun ## Students and interns: let's work together. I mentor students on AI security, evaluation and agentic systems. Start with the reading list, then email me with a paper of mine you'd like to extend. - [Reading list for new researchers →](https://yazan.boshmaf.com/students.md) - [QCRI research internships ↗](https://www.hbku.edu.qa/en/qcri/contact) - [Ask about mentorship →](https://yazan.boshmaf.com/#contact) ## Contact yazan at boshmaf dot com +974 445-[four one five five two] (office) ## Office HBKU Research Complex\ RC-B1-1190, Room A146\ Education City\ Doha, Qatar ## Elsewhere - [Google Scholar](https://scholar.google.com/citations?user=oDTfXXYAAAAJ) - [dblp](https://dblp.uni-trier.de/pers/hd/b/Boshmaf:Yazan) - [LinkedIn](https://linkedin.com/in/boshmaf) - [X / Twitter](https://twitter.com/boshmaf) - [News feed (Atom)](https://yazan.boshmaf.com/feed.xml)