arXiv AI By Bingzheng Wang, Xiaoyan Gu, Hongbo Xu, Hongcheng Li, Zimo Yu, Jiang Zhou, Weiping Wang, Wu Liu

Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistency

Read the original on arXiv AI →

Backdoor Sentinel introduces Temporal Noise Consistency (TNC), a new phenomenon where backdoor activation disrupts noise prediction consistency across adjacent diffusion timesteps, while clean inputs remain stable. Leveraging TNC, the authors propose TNC-Defense, a closed‑loop gray‑box framework that includes TNC‑Detect for auditors to identify and localize anomalous timesteps without accessing model weights, and TNC‑Detox for service providers to perform trigger‑agnostic, timestep‑aware corrections that suppress backdoor behavior. Experiments on five backdoor attacks show an 11% improvement in detection accuracy and a 98.5% invalidation rate of triggered samples with minimal impact on generation quality.

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.

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
Hugging Face Trending Papers
Jul 29

ToxScreen: Detecting Whether an LLM Has Been Poisoned

As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.

arXiv Machine Learning
Jul 30

ToxScreen: Detecting Whether an LLM Has Been Poisoned

arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.

By Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim, Andrew Draganov