neural network security

Adversarial-Inspired Backdoor Defense via Bridging Backdoor and Adversarial Attacks AAAI 2025 Attention-Imperceptible Backdoor Attacks on Vision Transformers AAAI 2025 Backdoor Defense via Enhanced Splitting and Trap Isolation ICCV 2025 SDBF: Steep-Decision-Boundary Fingerprinting for Hard-Label Tampering Detection of DNN Models CVPR 2025 Test-Time Backdoor Detection for Object Detection Models CVPR 2025 Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024 BAN: Detecting Backdoors Activated by Adversarial Neuron Noise NeurIPS 2024 Beyond Slow Signs in High-fidelity Model Extraction NeurIPS 2024 Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack CVPR 2024 Defending Against Backdoor Attacks by Layer-wise Feature Analysis (Extended Abstract) IJCAI 2024 Invisible Backdoor Attack against 3D Point Cloud Classifier in Graph Spectral Domain AAAI 2024 PKAD: Pretrained Knowledge is All You Need to Detect and Mitigate Textual Backdoor Attacks EMNLP 2024 Temporal-Distributed Backdoor Attack against Video Based Action Recognition AAAI 2024 United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories NeurIPS 2024 WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks NeurIPS 2024 Architectural Backdoors in Neural Networks CVPR 2023 BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning NeurIPS 2023 Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks NeurIPS 2023 Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency CVPR 2023 Distilling Cognitive Backdoor Patterns within an Image ICLR 2023 Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion Interspeech 2023 One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training ICCV 2023 Poisoning-Based Backdoor Attacks in Computer Vision AAAI 2023 TrojViT: Trojan Insertion in Vision Transformers CVPR 2023 You Are Catching My Attention: Are Vision Transformers Bad Learners Under Backdoor Attacks? CVPR 2023