arXiv Computation and Language September 1, 2026 By Oscar Chew, Po-Yi Lu, Jayden Lin, Kuan-Hao Huang, Hsuan-Tien Lin

PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models

Read the original on arXiv Computation and Language →

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.

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 Computation and Language.

arXiv AI

Jun 15

MirrorCheck: Efficient Adversarial Defense for Vision-Language Models

arXiv:2406. 09250v5 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses.

By Samar Fares, Klea Ziu, Toluwani Aremu, Nikita Durasov, Martin Tak\'a\v{c}, Pascal Fua, Ivan Laptev, Karthik Nandakumar

llms rag diffusion multimodal safety

arXiv Machine Learning

Aug 14

Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models

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

nlp multimodal 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

Hugging Face Trending Papers

Jul 7

AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models

Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization.

diffusion efficiency multimodal safety

arXiv AI

Aug 12

Covert Visual Prompt Injection against Commercial Multimodal Large Language Models

arXiv:2603. 29418v2 Announce Type: replace-cross Abstract: Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks.

By Meiwen Ding, Song Xia, Chenqi Kong, Xudong Jiang

llms multimodal safety

arXiv Machine Learning

Aug 17

Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack

arXiv:2605. 25194v2 Announce Type: replace Abstract: Adversarial images pose a severe security threat to multimodal large language models through prompt injection.

By Dongpeng Zhang, Ke Ma, Yangbangyan Jiang, Gaozheng Pei, Longtao Huang, Qianqian Xu, Qingming Huang