The paper introduces TRIM, a black‑box defense for backdoor attacks in computer vision models. TRIM identifies and removes malicious trigger regions at inference time using region‑based segmentation, adaptive trigger discovery via inpainting and diffusion, and selective purification, without needing model internals, training data, or clean samples. Experiments on various datasets and trigger types show TRIM reduces attack success rates to as low as 1.16% while maintaining high clean accuracy.
By Ahmed Abdelnaby, Mohamed Elmahallawy
arXiv:2609.31558v1 Announce Type: new
Abstract: Contrastive Language--Image Pretraining (CLIP) has emerged as a dominant vision backbone due to its strong transferability and zero-shot capabilities....
By Ahmed Abdelnaby, Mohamed Elmahallawy
arXiv:2511. 07210v3 Announce Type: replace-cross Abstract: Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications.
By Binyan Xu, Fan Yang, Di Tang, Xilin Dai, Kehuan Zhang
arXiv:2606. 25858v1 Announce Type: cross Abstract: Federated learning is vulnerable to backdoor attacks in which malicious clients inject poisoned updates while preserving benign-task performance.
By Kavindu Herath, Joshua C. Zhao, Saurabh Bagchi
arXiv:2507. 05113v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model.
By Binyan Xu, Fan Yang, Xilin Dai, Di Tang, Kehuan Zhang
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: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: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
DiSCO is a zero‑shot, black‑box defense for text‑to‑image models that operates solely at the prompt level. It expands prompts with a distribution‑guided suffix using beam search and contrastive scoring against safe and unsafe image pools generated by the target model, iteratively refining until safe content is produced. The method improves safety on the I2P benchmark under various red‑teaming attacks, reducing attack success rates by 37.7% and 25.13% while preserving semantic fidelity and image coherence.
By Tong Zhang, Motasem Alfarra, Carlos Hinojosa, Christos Louizos, Bernard Ghanem
arXiv:2511.14301v4 Announce Type: replace-cross
Abstract: Transformer-based models are highly susceptible to backdoor attacks via supervised fine-tuning (SFT). To red-team existing data-poisoning def...
By Eric Xue, Ruiyi Zhang, Pengtao Xie
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
The paper introduces TempJail, a temporal jailbreak framework targeting image‑to‑video generation models. It exploits a newly identified vulnerability where unsafe semantics arise from the composition of frames over time, rather than from single‑frame violations. By decomposing malicious captions into visual conditions and temporal instructions, and by employing controlled latent perturbations and template rewriting, TempJail achieves a 23.3 % higher attack success rate than prior methods on several commercial models.
By Qi Lu, Zehui Guo, David Yuanda Gan, Zijing Li, Hengda Zhang, Weijun Xu, Qiankun Zhang