This work studies clean-label temporal poisoning, where a fixed timestamp transformation is applied only to the target-class training streams, leaving their labels unchanged, which is the first clean-label backdoor attack evaluated on SNNs and neuromorphic event data.
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.
Backdoor attacks are a serious security threat to deep neural networks (DNNs) and remain largely underexplored for spiking neural networks (SNNs). Existing attacks primarily introduce spatiotemporal triggers that induce deviations in the spike distribution of poisoned samples relative to their clean counterparts. To ad...
Abdullah Arafat Miah, Kevin Vu, Yu Bi· 0 citations
TRIM (Trigger Removal by Identifying Manipulated Regions), a deployment-oriented black-box defense that detects and selectively removes backdoor triggers at inference time without requiring model internals, training data, or clean samples, is proposed.
Federated learning (FL)-based anomaly detection in next-generation (xG) networks is highly vulnerable to data poisoning, yet the impact of poisoning on model behaviour and decision structure remains poorly characterised. In this work, we present a system-level evaluation of label-flipping attacks across 306 configurati...
Salah Bin Ruba, P. B. Velloso, Pengwenlong Gu· 2026 International Conferenc...· 0 citations
RAMP is proposed, an attack enhancement method that uses a genetic algorithm to optimize reversed adversarial perturbations under black-box access and then injects them through functionality-preserving binary manipulations, which substantially improves attack effectiveness over trigger-only baselines.
Jin-Wen Xin, Dong-Ni Zhang, Chen-Yang Wang et al.· 0 citations
This survey unifies a fragmented literature spanning perception pipelines, input-adaptive neural inference, input-adaptive neural inference, and autoregressive and agentic systems and provides a threat-model taxonomy, consolidated quantitative comparisons, a defense review by control mechanism, and open challenges such...
These token-trigger mechanisms decompose into distinct SAE feature directions, with separate features for trigger detection, residual-stream propagation, and later language tracking, with this role-level decomposition most likely to transfer to other trigger-based backdoors, even when the payload, layers, or circuit lo...
Wissam Antoun, Francis Kulumba, Théo Lasnier et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.