Home
I am a Postdoctoral Researcher at Imperial College London’s Network and Systems Lab, working with Prof. Hamed Haddadi. My research focuses on trustworthy AI systems, robust AI agents, privacy-preserving machine learning, and verifiable AI infrastructure.
My recent work develops a coherent line from model-level privacy and LLM robustness to agent memory, private agent interaction, and trusted execution for deployed AI systems. I am particularly interested in making AI systems more private, robust, auditable, and deployable in real-world edge/cloud environments.
Model Privacy
Membership-inference risk mitigation for deployed ML models
LLM Robustness
Prompt-leakage and jailbreak resilience for deployed LLMs
Agent Execution
Confidential and protected execution for LLM agents on edge devices
Agent Memory
Privacy-aware memory and enforced erasure for agentic AI
Private Interaction
Privacy-preserving cryptographic protocols for agent negotiation
Verifiable Execution
Compound attestation and trusted infrastructure for AI workloads
Previously, I was a Doctoral (Ph.D.) Student in Computer Science at Umeå University, Sweden, funded by the Wallenberg AI, Autonomous Systems and Software Program (WASP). My Ph.D. research was supervised by Prof. Erik Elmroth, and I was a member of the Autonomous Distributed Systems Lab.
News
[March 2026] Our paper AgenTEE: Confidential LLM Agent Execution on Edge Devices was accepted at EuroMLSys 2026.
[March 2026] Our paper Towards Graph-Based Detection of Jailbreak and Prompt-Leakage Attacks in LLMs was accepted at EuroMLSys 2026.
[March 2026] Our paper DynaNoise: Dynamic Probabilistic Noise Injection for Defending Against Membership Inference Attacks was accepted at PETS 2026.
[September 2025] Our paper Reinforced model selection for resource efficient anomaly detection in edge clouds was published in Future Generation Computer Systems.
[January 2025] Started as Postdoctoral Researcher at Imperial College London.
[December 2024] Paper titled “Efficient Anomaly Detection for Edge Clouds: Mitigating Data and Resource Constraints” published at IEEE Access.
In a nutshell
- 2025–present: Postdoctoral Researcher, Imperial College London, UK
- 2024–2025: Machine Learning Engineer, OpenNebula Systems, Sweden
- 2020–2024: Ph.D. in Computer Science, Umeå University, Sweden
- 2017–2019: Master of Science in Computer Software Engineering, Amirkabir University, Iran
- 2011–2016: Bachelor of Science in Computer Software Engineering, Iran University of Science and Technology, Iran