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.
By Junjian Li, Xiaolong Liu, Peng Sun, Liantao Wu, Linghan Chen, Yudong Gao, Honglong Chen
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
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
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
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
DEFUSE is a backdoor detection framework for self‑supervised encoders that uses a conditional diffusion generative model to estimate representation‑conditioned image likelihoods. By fine‑tuning a pretrained diffusion model, DEFUSE performs semantic reconstruction in a reference encoder’s representation space, enabling it to detect backdoors without needing uninfected data or precomputed pseudo‑labels. Experiments show that DEFUSE outperforms existing detectors on both visual SSL and vision‑language encoders, reducing reliance on prior knowledge of the victim model or attack strategy.
By Tuo Chen, Jie Gui, Minjing Dong, Lanting Fang, Ju Jia, Benlei Cui, Jian Liu
arXiv:2604. 05809v2 Announce Type: replace-cross Abstract: This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally occur in ordinary textual inputs.
By Yiyang Zhang, Chaojian Yu, Ziming Hong, Yuanjie Shao, Qinmu Peng, Tongliang Liu, Xinge You
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
arXiv:2606. 02947v1 Announce Type: new Abstract: Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks.
By Ivan Saboli\'c, Marin Or\v{s}i\'c, Josip \v{S}ari\'c, Sven Lon\v{c}ari\'c
PEPPER (PErcePtion-Guided PERturbation) is a backdoor defense for text-to-image diffusion models that rewrites input captions into semantically distant yet visually similar versions, adding unobtrusive elements to disrupt trigger embeddings. By escaping the attacked neighborhood in the text embedding space, PEPPER reduces attack success, especially against text encoder-based attacks, while preserving generation quality. The method requires no training or model weight access and can be combined with existing defenses to achieve stronger, generalizable robustness.
By Oscar Chew, Po-Yi Lu, Jayden Lin, Kuan-Hao Huang, Hsuan-Tien Lin
Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the trigger, leaving the defender at a structural disadvantage when unknown backdoors may exist in a model.
UniGuardian is a training‑free detector for large language models that jointly identifies prompt injection, backdoor, and adversarial attacks—collectively called Prompt Trigger Attacks (PTA). It measures how structured prompt perturbations shift the model’s output distribution and uses a single‑forward strategy to detect attacks while generating text in a shared batched forward pass. Experiments show that UniGuardian accurately and efficiently identifies trigger‑activated prompts in LLMs.
By Huawei Lin, Yingjie Lao, Tony Geng, Tan Yu, Weijie Zhao