AI Security · Generative Models · Robust AI

Linfeng Jiang · 蒋霖锋 · Dav1

Building controllable and robust AI systems.

I am an undergraduate student at the University of Maryland, working on adversarial machine learning and generative-model security under the guidance of Andi Zhang. My research examines how adversarial evidence is formed, transferred, and interpreted across generative systems, with the broader goal of extending controllable and robust AI toward autonomous systems and embodied intelligence.

Research

Research I am pursuing

My work spans generative-model security, adversarial learning, robust neural computation, and evidence-grounded validation of autonomous systems.

02

Ongoing research

Adversarial Attacks on Diffusion Language Models

I investigate the security of diffusion language models, focusing on how adversarial inputs and generation-time manipulations affect model behavior, output reliability, and safety mechanisms.

I study attack design and evaluation settings while comparing the attack surfaces and robustness properties of diffusion-based generation with conventional autoregressive language models.

Diffusion language modelsAdversarial attacksAI security
03

Ongoing research

Spiking Neural Network (SNN) Robustness

I implement and evaluate spiking neural networks (SNNs), automate experiments across model checkpoints and configurations, and debug attack, detection, and reprogramming pipelines.

My analysis covers SNN robustness, detector behavior, temporal spiking activity, latency, and operation cost while keeping the experimental framework extensible to new datasets and attack families.

PyTorchSNNsReprogrammingRobustness evaluation
04

Ongoing research

Agent-Based Autonomous Driving Scenario Validation

I am developing an agent-based workflow that converts real-world crash reports and driving descriptions into executable scenarios and runs them in CARLA.

The pipeline combines source-grounded fact extraction, OpenDRIVE/OpenSCENARIO generation, trajectory checks, visual review, and evidence-guided repair to assess whether simulated behavior remains faithful to the source evidence.

Autonomous drivingAI agentsCARLAScenario validation
05

Emerging research direction

Background-Aware Carrier Integration and Adversarial Evidence

I hope to explore how carriers can be integrated more naturally into scene backgrounds, allowing their role to depend on a model's understanding of background semantics and global context rather than conspicuous foreground cues.

Context understandingBackground integrationCarrierAdversarial evidence

Publications

Selected research

2027

Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout

Title visually masked until the submission deadline.

AISTATS — on submission

Earlier work

I completed these works as a high school student, before the AI era—looking back, it is remarkable how quickly the world has changed.

Selected projects

From models to practical systems

Machine learning

Photovoltaic Output Forecasting

A CNN-LSTM pipeline for ultra-short-term time-series prediction and analysis of photovoltaic power output.

Python · CNN-LSTM · Time series
Cybersecurity

COFE Coin Security Mechanism Optimization

A security-focused study of the COFE Coin mechanism, examining system risks and proposing improvements to strengthen its protection model.

Digital currency · Security analysis · Mechanism design
Security systems

Centralized Security Dashboard

An executive-facing dashboard plan for consolidating security events, vulnerabilities, and organizational risk signals.

Dashboard design · Security · Project planning
Responsible AI

NIST AI Risk Management Accessibility

Concise inductive and deductive approaches for making AI risk-management concepts easier to apply in model assessment.

NIST AI RMF · Model assessment

Contact

Contact Me

I am actively seeking PhD positions and welcome research collaborations in AI and AI security.

ljiang19@umd.eduWeChat · dj884290GitHub ↗
Beyond research Manchester United crest Manchester United & Cristiano Ronaldo fan 🇵🇹