AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks

Yi Yu, Qixin Zhang, Shuhan Ye, Xun Lin, Qianshan Wei, Kun Wang, Wenhan Yang, Dacheng Tao, Xudong Jiang

ICLR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Attacks and defenses in sequential settings · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add projected-in-the-loop (strict projection forward, soft shifter backward) (ablation)PIL timing attack · DVS-Gesture binary B_1(8k)ASR: 84.3 -> 98.5Improved
add projected-in-the-loop on integer grid B_inf(3) (ablation)PIL timing attack · DVS-Gesture integer B_inf(3)ASR: 63.0 -> 85.0Improved
add budget penalty R_p (ablation)PIL timing attack · DVS-Gesture B_1ASR: binary 76.6 -> 98.5; integer 42.4 -> 79.1Improved
add capacity regularizer (ablation)PIL timing attack · DVS-Gesture binary B_1(8k)ASR: 98.5 -> 98.5No clear effect
add capacity regularizer on integer grid (ablation)PIL timing attack · DVS-Gesture integer B_inf(3)ASR: 77.6 -> 85.0Improved
use integer event grid instead of binary gridSNN victims · DVS-Gesture ResNet18 B_1(8k)ASR: 99.6 -> 65.4 (integer is more robust)Improved
increase time bins T from 20 to 40 on binary grid (ablation)PIL timing attack · DVS-Gesture binary B_1ASR: 90.6 -> 29.1Hurt
use targeted attack instead of untargeted (ablation)PIL timing attack · DVS-Gesture binary B_inf(1)ASR: 96.4 -> 26.8Hurt
use PLIF neurons instead of LIF (ablation)victim VGGSNN · DVS-Gesture integer B_1(16k)ASR: 79.1 -> 92.9Improved
adversarially train on integer grid with B_1(8k)VGGSNN · DVS-Gesturerobust accuracy: clean about 69%; robust mid-50% to above 60%Mixed
adversarially train on binary gridVGGSNN · DVS-Gestureclean accuracy: clean accuracy 22.92-48.26 vs 95.14 undefendedHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy