cs.LGAug 30, 2026

On the Resilience of Text-to-Video Diffusion Models to Hardware Faults

Authors: Zachary Coalson, A M Aahad, Stella Doehring, Zane Ma, Sanghyun Hong

Organizations: Oregon State University, Corvallis, OR, USA.

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

We present the first systematic study of the resilience of text-to-video (T2V) diffusion models under random hardware-level faults. While T2V models are widely used for automated video generation due to their ability to produce high-quality, temporally coherent, and realistic videos, their iterative denoising process and spatiotemporal dependencies introduce unique failure modes. We perform an extensive fault-injection study covering both computational and memory faults across three T2V models and a representative benchmark. Our results show that (1) a single fault can degrade overall performance by up to 3.7%, with semantic correctness more affected than perceptual quality; (2) memory faults are more damaging than computational faults, high-order exponent bits are particularly vulnerable, and the widely-used bfloat16 is more susceptible than alternative formats; and (3) 7-28% of faults cause visible artifacts, including semantic changes such as added objects, suggesting that single faults are sufficient to alter output semantics. Our findings reveal reliability risks in deployed T2V systems and motivate further research on improving fault resilience. Code: https://github.com/ztcoalson/T2V-Resilience.

Figures & tables

Figure 1: High-level architecture of a text-to-video diffusion model. The DiT backbone operates in latent space and is reused across denoising steps. In our study, we assess resilience by injecting random bitwise faults into the backbone’s weights and activations .
Figure 2: Impact of hardware faults on overall video quality and semantics. Average Total, Quality, and Semantic Scores over 100 trials for the fault-free (baseline), 2-bit memory fault, and 1-bit computational fault models. 95% CIs are within ±\pm 0.23 across all bars.
Figure 3: Resilience of model-level components to 2-bit memory faults for Latte. The average change across individual VBench metrics, categorized by maximum bit location, Transformer block index, and layer type.
Figure 4: Impact of computational faults across diffusion timesteps . The average change in individual VBench metrics for each (normalized) diffusion step at which faults were injected.
Figure 5: Impact of numerical representation for CogVideoX. The average Total Score under the fault-free (baseline) and 2-bit memory fault models. 95% CIs are within ±\pm 0.08 for all bars.
Figure 6: Example of qualitative fault outcomes for representative videos generated from OpenSora. We show 5 evenly spaced frames from each video. Prompt: “a dilapidated phone booth stood as a relic of a bygone era on the sidewalk, frozen in time.”
Figure 7: Distribution of qualitative fault outcomes for the 2-bit memory and 1-bit computational fault models (150 samples each).
Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 8: Impact of hardware faults on individual video quality and semantics metrics. For each metric, we report the average score over 100 trials for the fault-free (baseline), 2-bit memory fault, and 1-bit computational fault models. 95% CIs are within ±\pm 0.95.
Figure 9: Resilience of model-level components to 2-bit memory faults for OpenSora. The average change across individual VBench metrics, categorized by maximum bit location, Transformer block index, and layer type.
Figure 10: Resilience of model-level components to 2-bit memory faults for CogVideoX. The average change across individual VBench metrics, categorized by maximum bit location, Transformer block index, and layer type.
More in this topic

Video Diffusion Models

Video diffusion models generate or edit temporally coherent video by iteratively denoising latent sequences conditioned on text, images, motion, or other signals.

See all 697 papers

Explore similar work

CardsList

  1. Early Failure Detection and Intervention in Video Diffusion Models

    Mar 15, 2026Kwon Byung-Ki, Sohwi Lim, Nam Hyeon-Woo +2Video Diffusion ModelsT2V Generation

    Grad. School of Artificial Intelligence, POSTECH · School of Electrical Engineering, KAIST · Dept. of Electrical Engineering, POSTECH +1

  2. Does Semantic Noise Initialization Transfer from Images to Videos? A Paired Diagnostic Study

    Mar 3, 2026Yixiao Jing, Chaoyu Zhang, Zixuan Zhong +1Neural Network InitializationVideo Diffusion Models

    University of Michigan · University College London

  3. NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation

    Aug 31, 2026Yujiang Pu, Yu KongDiffusion Model GuidanceVideo Diffusion Models

    Michigan State University, East Lansing, MI 48824, USA