arXiv Computer Vision September 7, 2026 By Eun-Sol Park, MiSo Park, Yong-Goo Shin

FSPGD: Rethinking Black-box Attacks on Semantic Segmentation

Read the original on arXiv Computer Vision →

FSPGD introduces a feature-space black-box attack for semantic segmentation that targets intermediate representations rather than just output logits. The method uses a dual loss: an external loss to disrupt cross-model feature alignment and an internal loss to reduce consistency among same-class instances. Experiments on Pascal VOC 2012 and Cityscapes show that FSPGD outperforms existing logit-level and segmentation-specific attacks across CNN and Transformer backbones, and its adversarial examples improve robustness when used for training.

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 Computer Vision.

arXiv AI

Sep 1

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks

arXiv:2602.08136v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic...

By Md Rafi Ur Rashid, MD Sadik Hossain Shanto, Vishnu Asutosh Dasu, Shagufta Mehnaz

llms reinforcement-learning fine-tuning efficiency multimodal benchmarks safety

arXiv Machine Learning

Aug 4

DeepDefense: Robust Learning via Layer-Wise Gradient-Feature Alignment

arXiv:2511. 13749v2 Announce Type: replace Abstract: Deep neural networks are known to be vulnerable to adversarial perturbations, which are small, carefully crafted inputs that lead to incorrect predictions.

By Ci Lin, Tet Yeap, Iluju Kiringa

safety

arXiv Computer Vision

Sep 4

Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers

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

rag diffusion computer-vision multimodal

arXiv Machine Learning

Aug 6

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.

By Binyan Xu, Xilin Dai, Di Tang, Kehuan Zhang

llms multimodal safety

arXiv AI

Jun 24

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models

arXiv:2606. 24388v1 Announce Type: new Abstract: We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs).

By Simone Gallivanone, Hossein Khodadadi, Mauro Dore, Mauro Medda, Nicola Franco

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jun 10

Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction

arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.

By Lijia Yu, Jiuxin Cao, Yuchen Qiang, Changhao Chen, Yifei Huang, Bo Liu

llms multimodal safety

One email a morning, machine-written

Related stories

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks

DeepDefense: Robust Learning via Layer-Wise Gradient-Feature Alignment

Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models

Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction