English
Related papers

Related papers: Model-Targeted Poisoning Attacks with Provable Con…

200 papers

Deep neural networks are proven to be vulnerable to data poisoning attacks. Recently, a specific type of data poisoning attack known as availability attacks has led to the failure of data utilization for model learning by adding…

Cryptography and Security · Computer Science 2024-08-16 Yi Yu , Qichen Zheng , Siyuan Yang , Wenhan Yang , Jun Liu , Shijian Lu , Yap-Peng Tan , Kwok-Yan Lam , Alex Kot

In big data era, machine learning is one of fundamental techniques in intrusion detection systems (IDSs). However, practical IDSs generally update their decision module by feeding new data then retraining learning models in a periodical…

Machine Learning · Computer Science 2018-03-13 Pan Li , Qiang Liu , Wentao Zhao , Dongxu Wang , Siqi Wang

Adversaries can embed backdoors in deep learning models by introducing backdoor poison samples into training datasets. In this work, we investigate how to detect such poison samples to mitigate the threat of backdoor attacks. First, we…

Machine Learning · Computer Science 2023-06-21 Xiangyu Qi , Tinghao Xie , Jiachen T. Wang , Tong Wu , Saeed Mahloujifar , Prateek Mittal

\textbf{P}re-\textbf{T}rained \textbf{M}odel\textbf{s} have been widely applied and recently proved vulnerable under backdoor attacks: the released pre-trained weights can be maliciously poisoned with certain triggers. When the triggers are…

Cryptography and Security · Computer Science 2021-09-01 Linyang Li , Demin Song , Xiaonan Li , Jiehang Zeng , Ruotian Ma , Xipeng Qiu

Data poisoning -- the process by which an attacker takes control of a model by making imperceptible changes to a subset of the training data -- is an emerging threat in the context of neural networks. Existing attacks for data poisoning…

Machine Learning · Computer Science 2021-02-23 W. Ronny Huang , Jonas Geiping , Liam Fowl , Gavin Taylor , Tom Goldstein

Due to its distributed nature, federated learning is vulnerable to poisoning attacks, in which malicious clients poison the training process via manipulating their local training data and/or local model updates sent to the cloud server,…

Cryptography and Security · Computer Science 2022-10-05 Xiaoyu Cao , Zaixi Zhang , Jinyuan Jia , Neil Zhenqiang Gong

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the…

Machine Learning · Computer Science 2020-08-13 Vale Tolpegin , Stacey Truex , Mehmet Emre Gursoy , Ling Liu

Multimodal contrastive learning methods like CLIP train on noisy and uncurated training datasets. This is cheaper than labeling datasets manually, and even improves out-of-distribution robustness. We show that this practice makes backdoor…

Machine Learning · Computer Science 2022-03-29 Nicholas Carlini , Andreas Terzis

Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…

Machine Learning · Computer Science 2022-12-07 Marissa Connor , Vincent Emanuele

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-27 Loc Truong , Chace Jones , Brian Hutchinson , Andrew August , Brenda Praggastis , Robert Jasper , Nicole Nichols , Aaron Tuor

Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns about resilience to adversarial manipulation. This paper…

Machine Learning · Computer Science 2025-10-17 Harsh Chaudhari , Jamie Hayes , Matthew Jagielski , Ilia Shumailov , Milad Nasr , Alina Oprea

The increasing access to data poses both opportunities and risks in deep learning, as one can manipulate the behaviors of deep learning models with malicious training samples. Such attacks are known as data poisoning. Recent advances in…

Machine Learning · Computer Science 2023-06-29 Wenxiao Wang , Soheil Feizi

Imperceptible poisoning attacks on entire datasets have recently been touted as methods for protecting data privacy. However, among a number of defenses preventing the practical use of these techniques, early-stopping stands out as a…

Machine Learning · Computer Science 2022-04-20 Pedro Sandoval-Segura , Vasu Singla , Liam Fowl , Jonas Geiping , Micah Goldblum , David Jacobs , Tom Goldstein

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…

Machine Learning · Computer Science 2020-10-14 Ruoxin Chen , Jie Li , Chentao Wu , Bin Sheng , Ping Li

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…

Cryptography and Security · Computer Science 2026-05-27 Zedian Shao , Charles Fleming , Teodora Baluta

Machine learning models trained on data from the outside world can be corrupted by data poisoning attacks that inject malicious points into the models' training sets. A common defense against these attacks is data sanitization: first filter…

Machine Learning · Statistics 2021-12-06 Pang Wei Koh , Jacob Steinhardt , Percy Liang

Given access to a machine learning model, can an adversary reconstruct the model's training data? This work studies this question from the lens of a powerful informed adversary who knows all the training data points except one. By…

Cryptography and Security · Computer Science 2022-04-26 Borja Balle , Giovanni Cherubin , Jamie Hayes

Many modern machine learning classifiers are shown to be vulnerable to adversarial perturbations of the instances. Despite a massive amount of work focusing on making classifiers robust, the task seems quite challenging. In this work,…

Machine Learning · Computer Science 2018-11-07 Saeed Mahloujifar , Dimitrios I. Diochnos , Mohammad Mahmoody

Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks. Specifically, we propose a poisoning attack in which a…

Computation and Language · Computer Science 2021-07-13 Jun Wang , Chang Xu , Francisco Guzman , Ahmed El-Kishky , Yuqing Tang , Benjamin I. P. Rubinstein , Trevor Cohn

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Chengxiao Luo , Yiming Li , Yong Jiang , Shu-Tao Xia