Poster "backdoor attacks" Papers

32 papers found

Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks

Danni Yuan, Mingda Zhang, Shaokui Wei et al.

ICLR 2025arXiv:2312.06230
11
citations

Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool

Jiangtong Li, Dongyi Liu, Kun Zhu et al.

NEURIPS 2025arXiv:2412.17213
2
citations

Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning

Mingyuan Fan, Zhanyi Hu, Fuyi Wang et al.

ICLR 2025

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models

Zenghui Yuan, Jiawen Shi, Pan Zhou et al.

CVPR 2025arXiv:2503.16023
10
citations

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Xueyang Zhou, Guiyao Tie, Guowen Zhang et al.

NEURIPS 2025arXiv:2505.16640
13
citations

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

Bowei He, Lihao Yin, Huiling Zhen et al.

ICLR 2025arXiv:2502.06892
4
citations

DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders

Sizai Hou, Songze Li, Duanyi Yao

CVPR 2025arXiv:2411.16154
2
citations

FedRACE: A Hierarchical and Statistical Framework for Robust Federated Learning

Gang Yan, Sikai Yang, Wan Du

NEURIPS 2025

Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning

Ye Li, Yanchao Zhao, chengcheng zhu et al.

CVPR 2025arXiv:2409.19601
2
citations

MARS: A Malignity-Aware Backdoor Defense in Federated Learning

Wei Wan, Ning Yuxuan, Zhicong Huang et al.

NEURIPS 2025arXiv:2509.20383
4
citations

Monitoring Latent World States in Language Models with Propositional Probes

Jiahai Feng, Stuart Russell, Jacob Steinhardt

ICLR 2025arXiv:2406.19501
22
citations

Seal Your Backdoor with Variational Defense

Ivan Sabolic, Matej Grcic, Siniša Šegvić

ICCV 2025arXiv:2503.08829
1
citations

SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation

He Yang, Dongyi Lv, Song Ma et al.

NEURIPS 2025

Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models

Zhaoyi Liu, Huan Zhang

CVPR 2025arXiv:2502.18290
9
citations

Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification

Xiaobao Wang, Ruoxiao Sun, Yujun Zhang et al.

NEURIPS 2025arXiv:2509.26032
2
citations

Where the Devil Hides: Deepfake Detectors Can No Longer Be Trusted

Shuaiwei Yuan, Junyu Dong, Yuezun Li

CVPR 2025arXiv:2505.08255
2
citations

Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers

Xin Zhao, Xiaojun Chen, Bingshan Liu et al.

NEURIPS 2025arXiv:2510.13462

Adversarial Feature Map Pruning for Backdoor

Dong HUANG, Qingwen Bu

ICLR 2024arXiv:2307.11565
5
citations

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP

Jiawang Bai, Kuofeng Gao, Shaobo Min et al.

CVPR 2024arXiv:2311.16194
68
citations

Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks

Wenhan Yang, Jingdong Gao, Baharan Mirzasoleiman

ICML 2024arXiv:2310.05862
18
citations

Causality Based Front-door Defense Against Backdoor Attack on Language Models

Yiran Liu, Xiaoang Xu, Zhiyi Hou et al.

ICML 2024

Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization

Xingyi Zhao, Depeng Xu, Shuhan Yuan

ICML 2024

Event Trojan: Asynchronous Event-based Backdoor Attacks

Ruofei Wang, Qing Guo, Haoliang Li et al.

ECCV 2024arXiv:2407.06838
6
citations

Fisher Calibration for Backdoor-Robust Heterogeneous Federated Learning

Wenke Huang, Mang Ye, zekun shi et al.

ECCV 2024
7
citations

Flatness-aware Sequential Learning Generates Resilient Backdoors

Hoang Pham, The-Anh Ta, Anh Tran et al.

ECCV 2024arXiv:2407.14738
1
citations

IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency

Linshan Hou, Ruili Feng, Zhongyun Hua et al.

ICML 2024arXiv:2405.09786
41
citations

SHINE: Shielding Backdoors in Deep Reinforcement Learning

Zhuowen Yuan, Wenbo Guo, Jinyuan Jia et al.

ICML 2024

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models

Zhongqi Wang, Jie Zhang, Shiguang Shan et al.

ECCV 2024arXiv:2407.04215
28
citations

TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors

Yichuan Mo, Hui Huang, Mingjie Li et al.

ICML 2024arXiv:2409.05294
29
citations

TrojVLM: Backdoor Attack Against Vision Language Models

Weimin Lyu, Lu Pang, Tengfei Ma et al.

ECCV 2024arXiv:2409.19232
25
citations

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening

Siyuan Cheng, Guangyu Shen, Kaiyuan Zhang et al.

ECCV 2024arXiv:2407.11372
1
citations

WBP: Training-time Backdoor Attacks through Hardware-based Weight Bit Poisoning

Kunbei Cai, Zhenkai Zhang, Qian Lou et al.

ECCV 2024