PaperScope
LIVE · 2026-09-29 05:40 UTC

Let the Neurons Die: Exploiting ReLU-Induced Model Degradation

Kexin Li, Wenjun Qiu, Joshua Abraham, Aditi Maheshwari, David Lie

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.35528 v1
Category
Submitted
2026-09-28

Abstract

Rectified linear unit (ReLU) networks can suffer from dying neurons, where units with persistently negative pre-activations produce zero outputs, blocking gradients through their activations. To exploit this failure mode, we present three training-time availability attacks based on data ordering and poisoning. We begin with the basic dynamic data-ordering attack (DOA), which greedily constructs a training prefix by selecting the next example that minimizes the target layer's post-update weight sum, aiming to push ReLU units toward negative pre-activations without modifying training samples or labels. We then develop two poisoning attacks, IG-DOA and IG-SKA, which use gradient inversion to synthesize class-conditioned samples by matching reference gradients in adverse model states constructed through data ordering or soft knockout, respectively. Soft knockout rearranges weights across adjacent layers to concentrate negative contributions. On a fully connected ReLU network trained on MNIST, ordering 100 of 60,000 training examples reduces test accuracy from 96% to 95% after only five epochs. Adding 200 poisoned samples from a single class reduces test accuracy to approximately 86-88% after five epochs in most evaluated conditions, compared with approximately 96% under clean training. These results demonstrate that ReLU-targeted data ordering and poisoning can impair learning without directly modifying the victim model's parameters.

Comment: Accepted to the Trustworthy AI for Good (AI4Good) Workshop @ ICML 2026 in Seoul, South Korea; Presented as a poster on July 10, 2026

arXiv abs page · PDF · same-day batch