113 citations · 621 across the 55 of their papers we have counts for
10 papers · 1 filter
Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation
Ziqi Zhou, Yifan Hu, Yufei Song +5
The Segment Anything Model (SAM) achieves remarkable performance in visual segmentation. The latest SAM3 extends promptable segmentation to concept-level prediction, broadening the…
Imperceptible and Reversible Adversarial Examples against Vision-Language Models for Privacy Protection
Qi Lu, Ziqi Zhou, Yufei Song +5
Vision Language Models (VLMs) offer powerful multimodal ability but also expose users to text-based privacy attacks where adversaries crawl online photos and query VLMs to extract…
Test-Time Backdoor Detection for Object Detection Models
Hangtao Zhang, Yichen Wang, Shihui Yan +7
Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. De…
Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
Hangtao Zhang, Shengshan Hu, Yichen Wang +5
Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor a…
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
Ziqi Zhou, Minghui Li, Wei Liu +7
With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trai…
Detecting and Corrupting Convolution-based Unlearnable Examples
Minghui Li, Xianlong Wang, Zhifei Yu +4
Convolution-based unlearnable examples (UEs) employ class-wise multiplicative convolutional noise to training samples, severely compromising model performance. This fire-new type o…
Downstream-agnostic Adversarial Examples
Ziqi Zhou, Shengshan Hu, Ruizhi Zhao +4
Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users…
InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features
Mingfu Xue, Xin Wang, Yinghao Wu +3
Intellectual property (IP) protection for Deep Neural Networks (DNNs) has raised serious concerns in recent years. Most existing works embed watermarks in the DNN model for IP prot…
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label
Shengshan Hu, Ziqi Zhou, Yechao Zhang +4
Due to its powerful feature learning capability and high efficiency, deep hashing has achieved great success in large-scale image retrieval. Meanwhile, extensive works have demonst…
Self-Supervised Adversarial Example Detection by Disentangled Representation
Zhaoxi Zhang, Leo Yu Zhang, Xufei Zheng +2
Deep learning models are known to be vulnerable to adversarial examples that are elaborately designed for malicious purposes and are imperceptible to the human perceptual system. A…