Writing
Blog
Research write-ups on LLM backdoors and AI safety, paper reviews and reproductions, and notes from projects in NLP, speech, and systems.
Re-running a Vulnerability Detection Benchmark, More Carefully
I reproduced Devign (NeurIPS 2019) from scratch on the authors' own data. It lands 11 points below the paper, two-thirds of its test set leaks through shared commits, and a plain CNN beats it.
Read post
MECP-GAP: Mobility-Aware MEC Planning via GNNs
A review and implementation of MECP-GAP, a graph-neural-network approach to partitioning 5G base stations into MEC service regions that minimizes handover cost under load-balancing constraints.
Read postA Watchdog Model for Backdoored LoRA Adapters
Training a small distilled model to recognize the statistical fingerprint of a backdoored language model, instead of searching for a known trigger word.
Read post
The Sentinel's Dilemma: Guarding AI from Hidden Threats
A survey of backdoor attacks on large language models — how hidden triggers are implanted during training, and the detection and defense strategies emerging against them.
Read postTurning a Backdoor's Step Function Into a Ramp
A research design for eliciting a hidden model behavior by amplifying the exact fine-tuning change that planted it, then dialing that amplification back down to isolate the trigger.
Read postAuditing Backdoors: From a Flag to a Causal Proof
Extending a trigger-reconstruction pipeline for fine-tuned LLMs with a stricter auditing layer that separates a plausible-looking flag from actual proof of a backdoor.
Read postToward a Field-Based View of LLM Backdoors
A design study exploring whether a backdoor can be caught by looking at everything fine-tuning changed, rather than searching for a trigger or a target string.
Read post
Building a Weakness Zoo to Stress-Test a Backdoor Scanner
Deliberately building harder backdoor variants to find the blind spots of a state-of-the-art LLM backdoor scanner.
Read postStarting Point: Vision-Language Models for Dental X-rays
Early exploration of applying medical vision-language models to dental panoramic radiographs.
Read postComparing Five Ways to Catch a Backdoor, Live
A laptop-friendly lab for finetuning a small backdoored model and comparing several detection signals on clean vs. triggered inputs.
Read post
FTT-NAS: Implementation and Review
An implementation and review of FTT-NAS (Fault-Tolerant Neural Architecture Search), covering the MiBB feature-fault and adSAF weight-fault models for neural networks on unreliable hardware.
Read postUnderstanding BackdoorBench: A Comprehensive Benchmark for AI Security
A walkthrough of BackdoorBench, the standardized benchmark for evaluating backdoor attacks and defenses in deep learning — what it measures, why it matters, and how to use it.
Read post
Wav2Vec2 Sentiment Analysis Using Shemo Dataset
Fine-tuning Wav2Vec2 for Persian speech emotion recognition on the ShEMO dataset, combining audio features with text transcripts for robust sentiment classification.
Read post
Psychological Health Chatbot: Enhancing Mental Well-being with AI
A Persian-language mental-health chatbot built with transformer-based NLP, published at the AbjadNLP workshop — data collection, model training, and evaluation.
Read postOsmium Project Tasks
An Android app that estimates cellular base-station locations from RSSI and GPS measurements using circular lateration.
Read postMultimodal Sentiment Analysis Project(Persian-3classes)
Predicting sentiment from Persian Instagram posts by fusing VGG-16 image features with a bidirectional LSTM over the text.
Read postProject Iridium
A Docker-based network simulation with attacker, victim, and web-server stations: port scanning, credential testing, and data exfiltration in a sandbox.
Read postMy Internship at the NLP Lab
Notes from my research internship at the IUST NLP Lab — the papers I read and the Coursera courses I took along the way.
Read post