Blog

a look inside my head

Literature Review: Prompt Injection Attack to Tool Selection in LLM Agents

3 min read · June 21, 2025

2025 · Adversarial AI LLM Agents Prompt Injection Tool Selection Security · research
Literature Review: A Practical Memory Injection Attack against LLM Agents

4 min read · June 21, 2025

2025 · LLM Agents Adversarial AI Trustworthy AI Agentic AI AI Security · research
Creative: Blink and You'll Miss It

3 min read · June 21, 2025

2025 · creative
Literature Review: COSMIC: Generalized Refusal Direction Identification in LLM Activations

4 min read · June 14, 2025

2025 · Interpretability Trustworthy AI Adversarial AI LLM AI Safety · research
Literature Review: Layer-Gated Sparse Steering for Large Language Models

3 min read · June 14, 2025

2025 · Interpretability Steering Sparse Autoencoder Trustworthy AI LLM · research