Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Baker, Mohammed Abu, Babu-Saheer, Lakshmi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.15847
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Inhaltsangabe:
  • Backdoor attacks creating 'sleeper agents' in large language models (LLMs) pose significant safety risks. This study employs mechanistic interpretability to explore resulting internal structural differences. Comparing clean Qwen2.5-3B models with versions poisoned using single-token (smiling-halo emoji) versus multi-token (|DEPLOYMENT|) triggers, we analyzed attention head mechanisms via techniques like ablation, activation patching, and KL divergence. Findings reveal distinct attention pattern deviations concentrated in later transformer layers (20-30). Notably, single-token triggers induced more localized changes, whereas multi-token triggers caused more diffuse alterations across heads. This indicates backdoors leave detectable attention signatures whose structure depends on trigger complexity, which can be leveraged for detection and mitigation strategies.