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

20 March 2025

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

20 / 20 papers shown

Title
Adversarial Attacks in Multimodal Systems: A Practitioner's Survey Shashank Kapoor Sanjay Surendranath Girija Lakshit Arora Dipen Pradhan Ankit Shetgaonkar Aman Raj AAML 152 0 0 06 May 2025
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning Zhifang Zhang Shuo He Bingquan Shen Lei Feng Lei Feng AAML 112 1 0 29 Dec 2024
TrojVLM: Backdoor Attack Against Vision Language Models Weimin Lyu Lu Pang Tengfei Ma Haibin Ling Chao Chen MLLM 81 11 0 28 Sep 2024
Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models Zhenyang Ni Rui Ye Yuxian Wei Zhen Xiang Yanfeng Wang Siheng Chen AAML 87 13 0 19 Apr 2024
Test-Time Backdoor Attacks on Multimodal Large Language Models Dong Lu Tianyu Pang Chao Du Qian Liu Xianjun Yang Min Lin AAML 131 24 0 13 Feb 2024
Visual Instruction Tuning Haotian Liu Chunyuan Li Qingyang Wu Yong Jae Lee SyDa VLM MLLM 569 4,910 0 17 Apr 2023
Backdoor Attacks to Pre-trained Unified Foundation Models Zenghui Yuan Yixin Liu Kai Zhang Pan Zhou Lichao Sun AAML 71 11 0 18 Feb 2023
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models Junnan Li Dongxu Li Silvio Savarese Steven C. H. Hoi VLM MLLM 429 4,642 0 30 Jan 2023
Backdoor Attacks on Crowd Counting Yuhua Sun Tailai Zhang Xingjun Ma Pan Zhou Jian Lou Zichuan Xu Xing Di Yu Cheng Lichao AAML 57 15 0 12 Jul 2022
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning Baoyuan Wu Hongrui Chen Ruotong Wang Zihao Zhu Shaokui Wei Danni Yuan Chaoxiao Shen ELM AAML 96 144 0 25 Jun 2022
Flamingo: a Visual Language Model for Few-Shot Learning Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr ... Mikolaj Binkowski Ricardo Barreira Oriol Vinyals Andrew Zisserman Karen Simonyan MLLM VLM 418 3,602 0 29 Apr 2022
How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data Zhiyuan Zhang Lingjuan Lyu Weiqiang Wang Lichao Sun Xu Sun 70 36 0 03 Sep 2021
DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation Han Qiu Yi Zeng Shangwei Guo Tianwei Zhang Meikang Qiu B. Thuraisingham AAML 78 192 0 13 Dec 2020
Weight Poisoning Attacks on Pre-trained Models Keita Kurita Paul Michel Graham Neubig AAML SILM 138 453 0 14 Apr 2020
A new Backdoor Attack in CNNs by training set corruption without label poisoning Mauro Barni Kassem Kallas B. Tondi AAML 112 358 0 12 Feb 2019
Backdooring Convolutional Neural Networks via Targeted Weight Perturbations Jacob Dumford Walter J. Scheirer AAML 71 120 0 07 Dec 2018
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning Xinyun Chen Chang-rui Liu Yue Liu Kimberly Lu Basel Alomair AAML SILM 143 1,853 0 15 Dec 2017
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain Tianyu Gu Brendan Dolan-Gavitt S. Garg SILM 130 1,782 0 22 Aug 2017
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering Yash Goyal Tejas Khot D. Summers-Stay Dhruv Batra Devi Parikh CoGe 352 3,270 0 02 Dec 2016
Microsoft COCO Captions: Data Collection and Evaluation Server Xinlei Chen Hao Fang Nayeon Lee Ramakrishna Vedantam Saurabh Gupta Piotr Dollar C. L. Zitnick 224 2,493 0 01 Apr 2015