English
Related papers

Related papers: Mitigating Backdoor Poisoning Attacks through the …

200 papers

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Cryptography and Security · Computer Science 2023-07-28 Nikhil Kandpal , Matthew Jagielski , Florian Tramèr , Nicholas Carlini

In a backdoor attack, an adversary injects corrupted data into a model's training dataset in order to gain control over its predictions on images with a specific attacker-defined trigger. A typical corrupted training example requires…

Machine Learning · Computer Science 2023-10-31 Rishi D. Jha , Jonathan Hayase , Sewoong Oh

This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a 'backdoor poisoning' attack on NLP models. Our poisoning attack utilizes conditional…

Computation and Language · Computer Science 2020-10-07 Alvin Chan , Yi Tay , Yew-Soon Ong , Aston Zhang

With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific…

Machine Learning · Computer Science 2022-07-12 Chang Yue , Peizhuo Lv , Ruigang Liang , Kai Chen

In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable complement to existing…

Cryptography and Security · Computer Science 2022-06-17 Shawn Shan , Arjun Nitin Bhagoji , Haitao Zheng , Ben Y. Zhao

Neural networks are vulnerable to backdoor poisoning attacks, where the attackers maliciously poison the training set and insert triggers into the test input to change the prediction of the victim model. Existing defenses for backdoor…

Cryptography and Security · Computer Science 2024-05-21 Yuhao Zhang , Aws Albarghouthi , Loris D'Antoni

Backdoor and data-poisoning attacks can flip predictions with tiny training corruptions, yet a sharp theory linking poisoning strength, overparameterization, and regularization is lacking. We analyze ridge least squares with an unpenalized…

Machine Learning · Statistics 2026-01-06 Donald Flynn , Diego Granziol

Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly…

Machine Learning · Computer Science 2025-04-08 Min Liu , Alberto Sangiovanni-Vincentelli , Xiangyu Yue

Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training can be vulnerable to poisoning and backdoor attacks by one or…

Cryptography and Security · Computer Science 2026-04-06 Oğuzhan Ersoy , Nikolay Blagoev , Jona te Lintelo , Stefanos Koffas , Marina Krček , Stjepan Picek

In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Mozhgan Pourkeshavarz , Mohammad Sabokrou , Amir Rasouli

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

Machine Learning · Computer Science 2024-09-05 Ivan Sabolić , Ivan Grubišić , Siniša Šegvić

Predicitions made by neural networks can be fraudulently altered by so-called poisoning attacks. A special case are backdoor poisoning attacks. We study suitable detection methods and introduce a new method called Heatmap Clustering. There,…

Machine Learning · Computer Science 2022-04-28 Lukas Schulth , Christian Berghoff , Matthias Neu

Code LLMs are increasingly employed in software development. However, studies have shown that they are vulnerable to backdoor attacks: when a trigger (a specific input pattern) appears in the input, the backdoor will be activated and cause…

Cryptography and Security · Computer Science 2025-10-07 Chenyu Wang , Zhou Yang , Yaniv Harel , David Lo

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where…

Computation and Language · Computer Science 2024-11-28 Chen Chen , Yuchen Sun , Xueluan Gong , Jiaxin Gao , Kwok-Yan Lam

Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…

Machine Learning · Computer Science 2026-03-31 Osama Wehbi , Sarhad Arisdakessian , Omar Abdel Wahab , Azzam Mourad , Hadi Otrok , Jamal Bentahar

In a backdoor attack, an attacker injects corrupted examples into the training set. The goal of the attacker is to cause the final trained model to predict the attacker's desired target label when a predefined trigger is added to test…

Machine Learning · Computer Science 2022-10-13 Jonathan Hayase , Sewoong Oh

Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned…

Computation and Language · Computer Science 2021-06-04 Fanchao Qi , Mukai Li , Yangyi Chen , Zhengyan Zhang , Zhiyuan Liu , Yasheng Wang , Maosong Sun

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Cryptography and Security · Computer Science 2026-01-06 Eric Xue , Ruiyi Zhang , Pengtao Xie

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works require high computational overhead or backdoor attack…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Mingfu Xue , Yinghao Wu , Zhiyu Wu , Yushu Zhang , Jian Wang , Weiqiang Liu