Preprint
Aug 2026
Beyond Over-Refusal: Defending Indirect Prompt Injection via Latent Instruction Manifolds
AEGIS (Adaptive Ensemble Guard for Injection Shielding) extracts instruction-sensitive projectors to identify malicious instructions and leverages a Unified Multi-Layer Consensus mechanism that aggregates topologically distinct signals across the network depth.
Jia-Hao Chen, Ruiping Yin, Xinfeng Li et al.
· 0 citations