Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models

Computer Science > Computation and Language

[Submitted on 11 Sep 2026]

Title:Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models

View PDF HTML (experimental)Abstract:We identify \textbf{Harmfulness Propagation Dynamics (HPD)}: for harmful prompts, the projection of the last-token hidden state onto a learned harm direction rises monotonically with transformer depth, whereas benign prompts remain flat or oscillatory. This cross-layer signature reflects harmful intent as a \emph{progressively resolved} semantic property: surface form appears early, while pragmatic intent consolidates later, making the \emph{trajectory shape} more informative than any single-layer snapshot. Moreover, LDA-based harm directions, learned per layer, remain stable across random splits (pairwise cosine similarity $>0.97$), supporting the projection sequence as a reproducible structured signal. Building on HPD, we introduce \textbf{\herald{}} (\textbf{H}armful \textbf{E}ncoding \textbf{R}ecognition via \textbf{A}ctivation \textbf{L}ayer \textbf{D}ynamics). This lightweight input moderator extracts a seven-dimensional feature record, slope, curvature, monotonicity, onset layer, and related statistics from the cross-layer projection sequence and classifies it with a 288-parameter MLP. \herald{} stores one $d$-dimensional direction per layer ($262$\,KB for a 32-layer, $d{=}4096$ model), requires no gradient computation during training, and adds only $2.6{\times}10^{-6}$ prefill FLOPs at inference. Across eight prompt-harmfulness benchmarks and four model families, \herald{} achieves an average F1 of $89.3$ on OLMo2-7B, surpassing all tested guard models on adversarial jailbreak detection ($98.4$ vs.\ $96.9$ F1) and outperforming prior latent-based methods by $2.3$-$4.1$ F1 points on every backbone. Per-instance trajectories provide machine-readable audit records that reveal \emph{when} and \emph{how} harmfulness emerges, offering an interpretability advantage over single-layer approaches.

Submission history

From: Noor Noor S. Mohammad [view email][v1] Fri, 11 Sep 2026 21:04:55 UTC (1,527 KB)

References & Citations

Loading...

Bibliographic and Citation Tools

Bibliographic Explorer (What is the Explorer?)

Connected Papers (What is Connected Papers?)

Litmaps (What is Litmaps?)

scite Smart Citations (What are Smart Citations?)

Code, Data and Media Associated with this Article

alphaXiv (What is alphaXiv?)

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub (What is DagsHub?)

Gotit.pub (What is GotitPub?)

Hugging Face (What is Huggingface?)

ScienceCast (What is ScienceCast?)

Demos

Recommenders and Search Tools

Influence Flower (What are Influence Flowers?)

CORE Recommender (What is CORE?)

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.