时间就是一切:针对事件驱动脉冲神经网络的脉冲重定时攻击
Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks
AI总结:
本文提出了一种针对事件驱动脉冲神经网络的脉冲重定时攻击,通过重定时脉冲而非改变强度或计数来实现攻击,展示了其在多个基准上的高成功率。
摘要:
脉冲神经网络(SNNs)通过离散脉冲进行计算,并利用时间结构,但大多数对抗性攻击改变强度或事件计数而非时间。我们研究了一种仅改变时间的攻击者,在事件驱动的SNN中重定时现有脉冲,同时保持脉冲计数和幅度,从而保持速率不变。我们正式定义了一个容量为1的脉冲重定时威胁模型,其包含统一的三重预算:每个脉冲的抖动B_∞,总延迟B_1,以及篡改计数B_0。可行的对抗性示例必须满足时间线一致性和不重叠,这使搜索空间离散且受限。为了在大规模上优化此类重定时,我们使用了投影在回路(PIL)优化:移位概率日志产生可微的软重定时以供反向传播,而在正向传递中严格投影产生一个可行的离散计划,该计划在每一步都满足容量为1、不重叠和所选预算。目标最大化投影输入上的任务损失,并添加一个容量正则化器以及预算感知惩罚,这稳定了梯度并使优化与评估对齐。在事件驱动的基准(CIFAR10-DVS、DVS-Gesture、N-MNIST)和多样化的SNN架构上,我们评估了二进制和整数事件网格以及多种重定时预算,并测试了使用时间感知对抗训练训练的模型,以对抗仅改变时间的攻击。例如,在DVS-Gesture上,攻击在接触不到2%的脉冲的情况下达到高成功率(超过90%)。综合来看,我们的结果表明,脉冲重定时是一个实际且隐蔽的攻击面,当前的防御措施难以对抗,为事件驱动SNNs中的时间鲁棒性提供了明确的参考。代码可在https://github.com/yuyi-sd/Spike-Retiming-Attacks上获得。
英文摘要:
Spiking neural networks (SNNs) compute with discrete spikes and exploit temporal structure, yet most adversarial attacks change intensities or event counts instead of timing. We study a timing-only adversary that retimes existing spikes while preserving spike counts and amplitudes in event-driven SNNs, thus remaining rate-preserving. We formalize a capacity-1 spike-retiming threat model with a unified trio of budgets: per-spike jitter $\mathcal{B}_{\infty}$, total delay $\mathcal{B}_{1}$, and tamper count $\mathcal{B}_{0}$. Feasible adversarial examples must satisfy timeline consistency and non-overlap, which makes the search space discrete and constrained. To optimize such retimings at scale, we use projected-in-the-loop (PIL) optimization: shift-probability logits yield a differentiable soft retiming for backpropagation, and a strict projection in the forward pass produces a feasible discrete schedule that satisfies capacity-1, non-overlap, and the chosen budget at every step. The objective maximizes task loss on the projected input and adds a capacity regularizer together with budget-aware penalties, which stabilizes gradients and aligns optimization with evaluation. Across event-driven benchmarks (CIFAR10-DVS, DVS-Gesture, N-MNIST) and diverse SNN architectures, we evaluate under binary and integer event grids and a range of retiming budgets, and also test models trained with timing-aware adversarial training designed to counter timing-only attacks. For example, on DVS-Gesture the attack attains high success (over $90\%$) while touching fewer than $2\%$ of spikes under $\mathcal{B}_{0}$. Taken together, our results show that spike retiming is a practical and stealthy attack surface that current defenses struggle to counter, providing a clear reference for temporal robustness in event-driven SNNs. Code is available at https://github.com/yuyi-sd/Spike-Retiming-Attacks.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。