← Back to all news
arXiv Machine Learning By Roberto Ria\~no, Gorka Abad, Stjepan Picek, Aitor Urbieta

MeMark: Membrane-Space Watermarking for Spiking Neural Networks

Read the original on arXiv Machine Learning →

MeMark introduces a watermarking scheme for Spiking Neural Networks that embeds a multi‑bit identifier directly into the membrane state of selected Leaky Integrate‑and‑Fire neurons, rather than in the output head. The watermark is recoverable by comparing neuron firing thresholds, eliminating the need for a learned decoder. Experiments on various SNN architectures—including a 215.4M‑parameter SpikeGPT checkpoint—show that all 20 independent 64‑bit keys reliably pass verification under a 51/64 rule, remain robust after fine‑tuning, pruning, quantization, and output‑head replacement, and are not recovered by random keys or adaptive attacks within the tested threat model.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
6d ago

Spiking Neural Networks Are Harder to Steal: A Benchmark Study of Model Stealing Attacks

The paper investigates whether spiking neural networks (SNNs) are more resistant to model stealing attacks than conventional artificial neural networks (ANNs). By benchmarking four common attacks on MNIST, Fashion‑MNIST, and CIFAR‑10, the authors find that SNNs consistently yield surrogates with 10%–20% lower agreement and 15%–25% lower adversarial transferability compared to ANNs. The authors attribute this resilience to the spike‑based, time‑dependent dynamics of SNNs, which make their decision boundaries harder for ANN‑based surrogates to approximate.

By Ayana Moshruba, Maryam Parsa
benchmarkssafety
More like this →
arXiv Machine Learning
6d ago

Intellectual Property Protection of Hyperdimensional Computing Classifiers: Black-Box Ownership Verification via Model Watermarking

The paper investigates model watermarking for hyperdimensional computing (HDC) classifiers, adapting backdoor-based embedding to three prototype‑learning mechanisms. Across four benchmarks, error‑driven models (AdaptHD and OnlineHD) support ownership verification with minimal accuracy loss, while single‑pass Vanilla HDC requires higher trigger exposure and incurs larger accuracy penalties. The study also shows that watermarks can be overwritten, survive certain stress tests on FPGA, but may be lost during extraction or severe stress, highlighting both feasibility and limitations of HDC watermarking.

By Hamed Poursiami, Farshad Soleiman, Ahmad Tahmasivand, Guojing Cong, Thomas Potok, Khaled N. Khasawneh, Kai Zeng, Maryam Parsa
ragbenchmarks
More like this →
arXiv AI
Oct 19

SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks

SpikeQ introduces a spike‑guided post‑training quantization framework for spiking neural networks, selecting weight levels by simulating downstream neurons to minimize spike errors and designing a reset‑aware grid for pre‑fire membrane potential quantization that avoids spike flips. The method outperforms existing grids on seven image‑processing benchmarks, maintaining full‑precision accuracy with 2‑bit pre‑fire potentials and staying within 2.59 points of full precision at 4 bits while drastically reducing memory and energy usage.

By Kai Sun, Peibo Duan, Zhanglu Yan, Guowei Zhang, Yongsheng Huang, Levin Kuhlmann
computer-visionefficiencybenchmarks
More like this →