6 papers
DETOUR: A Practical Backdoor Attack against Object Detection
Dazhuang Liu, Yanqi Qiao, Rui Wang +2
Object detection (OD) is critical to real-world vision systems, yet existing backdoor attacks on detection transformers (DETRs) for OD tasks rely on patch-wise triggers optimized a…
PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers
Dazhuang Liu, Yanqi Qiao, Rui Wang +2
Vision Transformers (ViTs) have achieved remarkable success across vision tasks, yet recent studies show they remain vulnerable to backdoor attacks. Existing patch-wise attacks typ…
LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm
Dazhuang Liu, Yanqi Qiao, Rui Wang +2
Current black-box backdoor attacks in convolutional neural networks formulate attack objective(s) as single-objective optimization problems in single domain. Designing triggers in…
Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm
Yanqi Qiao, Dazhuang Liu, Rui Wang +1
While convolutional neural networks (CNNs) have achieved success in computer vision tasks, it is vulnerable to backdoor attacks. Such attacks could mislead the victim model to make…
FTA: Stealthy and Adaptive Backdoor Attack with Flexible Triggers on Federated Learning
Yanqi Qiao, Dazhuang Liu, Congwen Chen +2
Current backdoor attacks against federated learning (FL) strongly rely on universal triggers or semantic patterns, which can be easily detected and filtered by certain defense mech…
Constructing feature variation coefficients to evaluate feature learning capabilities of convolutional layers in steganographic detection algorithms of spatial domain
Ru Zhang, Sheng Zou, Jianyi Liu +2
Traditional steganalysis methods generally include two steps: feature extraction and classification.A variety of steganalysis algorithms based on CNN (Convolutional Neural Network)…