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

arXiv: https://arxiv.org/abs/2608.29598 · HTML: https://mlsanity.com/paper/2608.29598/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 26 of its 50 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 26 of 26)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [Text-to-image Diffusion Models in Generative AI: A Survey](https://mlsanity.com/paper/2303.07909/) (2023)
- [A Study of BFLOAT16 for Deep Learning Training](https://mlsanity.com/paper/1905.12322/) (2019)
- [T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation](https://mlsanity.com/paper/2407.14505/) (2024)
- [Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search](https://mlsanity.com/paper/1903.12269/) (2019)
- [Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation](https://mlsanity.com/paper/2307.06940/) (2023)
- [Restart Sampling for Improving Generative Processes](https://mlsanity.com/paper/2306.14878/) (2023)
- [Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks](https://mlsanity.com/paper/1906.01017/) (2019)
- [MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images](https://mlsanity.com/paper/2306.07257/) (2023)
- [GPUHammer: Rowhammer Attacks on GPU Memories are Practical](https://mlsanity.com/paper/2507.08166/) (2025)
- [LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation](https://mlsanity.com/paper/2511.00090/) (2025)
- [DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation](https://mlsanity.com/paper/2410.07151/) (2024)
- [ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering](https://mlsanity.com/paper/2503.16867/) (2025)
- [Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation](https://mlsanity.com/paper/2506.00329/) (2025)
- [PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips](https://mlsanity.com/paper/2412.07192/) (2024)
- [Characterizing a Neutron-Induced Fault Model for Deep Neural Networks](https://mlsanity.com/paper/2211.13094/) (2022)
- [Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models](https://mlsanity.com/paper/2406.03229/) (2024)
- [Breaking the HBM Bit Cost Barrier: Domain-Specific ECC for AI Inference Infrastructure](https://mlsanity.com/paper/2507.02654/) (2025)
- [Understanding the Landscape of Ampere GPU Memory Errors](https://mlsanity.com/paper/2508.03513/) (2025)

## Abstract (arXiv)

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: hrefhttps://github.com/ztcoalson/T2V-Resiliencehttps://github.com/ztcoalson/T2V-Resilience.