Publications
White papers, technical reports, and research essays across all three pillars.
Benchmarks for Evaluating Prompt-Injection Defenses in Tool-Using LLM Agents: A Comparative Threat-Model and Measurement Audit
AI Security
What Building a Model-Agnostic Research Pipeline Actually Took
AI Automation
Preserving Learning in Generative AI Tutoring Systems: Pedagogical Safety, Cognitive Effort, and Adaptive Scaffolding
Human Learning and Knowledge Systems
Agentic Binary Reverse Engineering: State of the Art, Architecture, Benchmarks, Failure Modes, and Research Agenda
AI Systems and Security
Agentic Patch Validation in Automated Vulnerability Repair
AI Systems and Security
Generative AI Tutors and Personalized Adaptive Learning Systems
Human Learning and Knowledge Systems
Effects of AI Assistance on Critical Thinking and Cognitive Offloading
Human Learning and Knowledge Systems
Tool-use reliability, function-calling robustness, and structured output enforcement
Applied Intelligence and Automation
Compound AI systems and orchestration patterns for multi-step automation
Applied Intelligence and Automation
Sandboxing and Capability Control for Tool-Using Autonomous Agents
AI Systems and Security
Tool-using LLM agent security and prompt-injection defenses
AI Systems and Security
Hardening Multi-Agent Systems Against Prompt Injection
AI Security · Prompt Injection · Multi-Agent Systems · Defenses · Hardening
NOW9000: A Voice-Based AI Jailbreak Game
Jailbreaking · Voice Agent · Guardrails · Prompt Injection · Social Engineering
Full-Vocabulary Glitch Token Census and ASR Validation Methodology Correction
LLM Security · Glitch Tokens · ASR Validation · Methodology
Auditing Glitcher's ASR Validation and Mining Coverage: Deterministic Decoding Bugs and Candidate Generation Gaps in Glitch Token Discovery
LLM Security · Glitch Tokens · Research Audit · Methodology
Prompt Injection, Tool Hijacking, and Data Exfiltration Defenses in RAG/Agent Systems
AI Security · Prompt Injection · RAG Security · Agent Security
Glitcher: Mining and Classifying Glitch Tokens in Large Language Models
LLM Security · Glitch Tokens · Tooling
Harnessing Large Language Models for Enhanced Malware Reverse Engineering
Malware · Reverse Engineering · LLM · SecTor 2023
Building a Model-Agnostic, Open AI Research Automation Pipeline
SupersededAI Automation
Exploiting Multi Agent Systems: How Prompt Injection Turns Collaboration into Compromise
SupersededAI Security · Prompt Injection · Multi-Agent Systems