arXiv AI October 1, 2026 By Junjian Li, Xiaolong Liu, Peng Sun, Liantao Wu, Linghan Chen, Yudong Gao, Honglong Chen

Learning Normal Diffusion Dynamics for Backdoor Defense in Text-to-Image Models

The paper introduces Normal Diffusion Dynamics Learning (NDDL), a defense framework for text-to-image diffusion models that learns normal transition dynamics from benign samples. By modeling structured, timestep‑dependent patterns across cross‑attention, latent, and noise spaces, NDDL detects backdoor attacks through deviations between observed and predicted diffusion trajectories. It also localizes triggers without prior knowledge by substituting low‑semantic words, and experiments show its effectiveness across diverse attacks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

diffusion

Hugging Face Trending Papers

3d ago

Learning Normal Diffusion Dynamics for Backdoor Defense in Text-to-Image Models

Backdoor attacks pose a serious threat to the secure deployment of text-to-image (T2I) diffusion models. Existing defenses typically detect backdoors from specific abnormal patterns in internal repres...

diffusion

arXiv AI

Jun 26

TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models

arXiv:2606. 26285v1 Announce Type: cross Abstract: Noise-based backdoor attacks on diffusion models typically rely on input-time trigger injection, untargeted activation, and out-of-distribution target generation.

By William Aiken, Paula Branco, Guy-Vincent Jourdan, Iosif-Viorel Onut

diffusion

arXiv Machine Learning

Jun 3

Backdooring Masked Diffusion Language Models

arXiv:2605. 19262v2 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored.

By Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou, Chengyu Huang, Pin-Yu Chen, Shengwei An

llms diffusion fine-tuning

arXiv Machine Learning

Aug 14

Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise

arXiv:2601. 21628v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy and copyright.

By Puwei Lian, Yujun Cai, Songze Li, Bingkun Bao

diffusion fine-tuning safety

arXiv Computer Vision

Sep 22

BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models

arXiv:2511.18921v2 Announce Type: replace Abstract: Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously ac...

By Juncheng Li, Yige Li, Hanxun Huang, Yunhao Chen, Xin Wang, Yixu Wang, Xingjun Ma, Yu-Gang Jiang

llms nlp multimodal benchmarks safety

arXiv Machine Learning

Sep 14

Certifying Concept Unlearning in Text-to-Image Diffusion Models

The paper introduces a certification framework for assessing concept unlearning in text-to-image diffusion models, offering high‑confidence guarantees with bounded error on residual concept leakage. Unlike prior methods that rely solely on attack success rates from automated prompt searches, this approach combines statistical certification with worst‑case analysis along concept‑relevant embedding directions to derive explicit upper bounds on leakage probability. Evaluations across NSFW content, artistic styles, and celebrity identities reveal that certified leakage bounds exceed standard attack success rates by 16.2%, highlighting significant residual risks overlooked by existing protocols.

By Mansi, Luca Marzari, Francesco Leofante

rag diffusion benchmarks safety

One email a morning, machine-written

Related stories

Learning Normal Diffusion Dynamics for Backdoor Defense in Text-to-Image Models

TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models

Backdooring Masked Diffusion Language Models

Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise

BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models

Certifying Concept Unlearning in Text-to-Image Diffusion Models