Truth Lies Deep: Countering Semantic Camouflage via Latent Intent Verification

arXiv cs.AIAugust 24, 2026en

arXiv:2608.20378v1 Announce Type: new Abstract: Safety alignment in Large Language Models (LLMs) is often superficial, relying on refusal mechanisms that trigger only at the final stages of generation without erasing the foundational knowledge of harmful concepts acquired during pretraining. This study demonstrates that this architectural disconnect leaves models vulnerable to Semantic Camouflage -- adversarial attacks that wrap harmful intent in benign narrative contexts (e.g., creative writing), effectively bypassing standard input and output guardrails. By analyzing the latent activation trajectories of three distinct Small Language Model (SLM) families (Phi-3, Qwen2.5, and Gemma-2b) unde

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning