Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs
Roberto Riaño, Gorka Abad, Stjepan Picek, Aitor Urbieta
cs.CR, cs.AI
Submitted: 2026-07-30
License: http://creativecommons.org/licenses/by/4.0/
The gist: Backdoor attacks on Spiking Neural Networks (SNNs) have primarily assumed dirty-label poisoning, in which triggered training samples are relabeled to an attacker-selected class.
Terminology
Abstract
Backdoor attacks on Spiking Neural Networks (SNNs) have primarily assumed dirty-label poisoning, in which triggered training samples are relabeled to an attacker-selected class. We study clean-label temporal poisoning, where a fixed timestamp transformation is applied only to the target-class training streams, leaving their labels unchanged. The transformation preserves the per-pixel, per-polarity event count exactly, making clean and triggered samples identical after temporal aggregation while altering the sequence processed by the SNN. Across three neuromorphic datasets and both convolutional and transformer-based victims, the attack reaches an ASR of 1.00 in the strongest configurations. We analyze the attack through poison-budget and trigger-shape ablations and evaluate established backdoor defenses adapted to spiking models. Defenses that collapse the time axis before inspection are blind by construction, while feature-space methods detect the poison only in selected settings. Our model-free detector, based on per-step event mass, detects the evaluated temporal transformations, demonstrating both the limitation of rate-collapsed defenses and the boundary of the attack's stealth. To our knowledge, this is the first clean-label backdoor attack evaluated on SNNs and neuromorphic event data.
Sources
- Data Poisoning-based Backdoor Attack Framework against Supervised Learning Rules of Spiking Neural Networks
- Gridbot: An autonomous robot controlled by a Spiking Neural Network mimicking the brain's navigational system
- Label-Consistent Backdoor Attacks
- CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processor
- Time-Distributed Backdoor Attacks on Federated Spiking Learning
- Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
- Spikewhisper: Temporal Spike Backdoor Attacks on Federated Neuromorphic Learning over Low-power Devices
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs