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
With the development of applications like autonomous driving, object detection has gained significant attention, while also highlighting critical vulnerabilities like backdoor attacks that severely co...
arXiv:2609.28239v1 Announce Type: new
Abstract: With the development of applications like autonomous driving, object detection has gained significant attention, while also highlighting critical vulne...
By Li Zeng, Mingcheng Duan, Longfei Fan, Hangtao Zhang, Xianlong Wang, Yanchun Li, Xia Wen, Leo Yu Zhang
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
The paper introduces STAIN-FL, a stealthy backdoor attack framework for federated video anomaly detection that uses natural surveillance conditions—such as low light, indoor settings, and crowd density—as contextual triggers. STAIN-FL manipulates anomaly labels and masks gradients to keep clean accuracy low while inducing trigger‑conditioned misclassification. Experiments on UCF‑Crime with I3D features show that sparse attacks remain undetectable, drop clean accuracy by less than 2%, yet achieve over 50% backdoor accuracy for hundreds of rounds under FedAvg and FedProx.
By Ashlinder Kaur, Purnima Murali Mohan, Zengxiang Li, Tram Truong-Huu
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: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
The paper investigates how dataset imbalance increases vulnerability to backdoor attacks and degrades existing defenses. It introduces Randomized Probability Perturbation (RPP), a black‑box framework that detects poisoned samples using only model output probabilities, providing provable detectability guarantees and a bound on false positives. Experiments on five benchmarks and multiple attacks show RPP outperforms state‑of‑the‑art defenses, especially under class imbalance.
By Miao Lin, Feng Yu, Rui Ning, Lusi Li, Jiawei Chen, Qian Lou, Mengxin Zheng, Chunsheng Xin, Hongyi Wu
arXiv:2607. 05516v2 Announce Type: replace-cross Abstract: Model-specific adversarial attacks have been extensively studied.
By Paul K. Mandal, Pavan Reddy, Tristan Malatynski
arXiv:2607. 05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied.
By Paul K. Mandal, Pavan Reddy, Tristan Malatynski
arXiv:2601. 12359v1 Announce Type: cross Abstract: Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards and induce harmful or unintended outputs.
By Anirudh Sekar, Mrinal Agarwal, Rachel Sharma, Akitsugu Tanaka, Jasmine Zhang, Arjun Damerla, Kevin Zhu
The paper introduces DAR (Discover-and-Relabel), a support‑persistent backdoor technique that remains effective even after models undergo clean‑data knowledge distillation. DAR discovers naturally occurring patterns in low‑dimensional feature subspaces via subspace clustering and then poisons labels of samples that satisfy these patterns. At inference, the backdoor is triggered by locally modifying the target image’s subspace, achieving attack accuracy comparable to state‑of‑the‑art methods while maintaining over 96% success after clean distillation.
By Junhoo Lee, Baekseung Kim, Seungyeon Kim, Nojun Kwak