English
Related papers

Related papers: Generalization Bound and New Algorithm for Clean-L…

200 papers

Generalization of machine learning models can be severely compromised by data poisoning, where adversarial changes are applied to the training data. This vulnerability has led to interest in certifying (i.e., proving) that such changes up…

Machine Learning · Computer Science 2025-07-16 Lukas Gosch , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar , Stephan Günnemann

In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor attack is an attack targeting the vulnerability of deep…

Cryptography and Security · Computer Science 2023-12-14 Peixin Zhang , Jun Sun , Mingtian Tan , Xinyu Wang

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Computation and Language · Computer Science 2025-10-07 Jiawei Kong , Hao Fang , Xiaochen Yang , Kuofeng Gao , Bin Chen , Shu-Tao Xia , Ke Xu , Han Qiu

This work provides the community with a timely comprehensive review of backdoor attacks and countermeasures on deep learning. According to the attacker's capability and affected stage of the machine learning pipeline, the attack surfaces…

Cryptography and Security · Computer Science 2020-08-04 Yansong Gao , Bao Gia Doan , Zhi Zhang , Siqi Ma , Jiliang Zhang , Anmin Fu , Surya Nepal , Hyoungshick Kim

We consider a model of robust learning in an adversarial environment. The learner gets uncorrupted training data with access to possible corruptions that may be affected by the adversary during testing. The learner's goal is to build a…

Machine Learning · Computer Science 2022-07-04 Idan Attias , Aryeh Kontorovich , Yishay Mansour

Modern machine learning (ML) systems demand substantial training data, often resorting to external sources. Nevertheless, this practice renders them vulnerable to backdoor poisoning attacks. Prior backdoor defense strategies have primarily…

Machine Learning · Computer Science 2024-03-19 Soumyadeep Pal , Yuguang Yao , Ren Wang , Bingquan Shen , Sijia Liu

Poison-only Clean-label Backdoor Attacks aim to covertly inject attacker-desired behavior into DNNs by merely poisoning the dataset without changing the labels. To effectively implant a backdoor, multiple \textbf{triggers} are proposed for…

Cryptography and Security · Computer Science 2025-10-08 Zhixiao Wu , Yao Lu , Jie Wen , Hao Sun , Qi Zhou , Guangming Lu

Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…

Cryptography and Security · Computer Science 2022-10-20 Yangyi Chen , Fanchao Qi , Hongcheng Gao , Zhiyuan Liu , Maosong Sun

Quantum classifiers are vulnerable to adversarial attacks that manipulate their input classical or quantum data. A promising countermeasure is adversarial training, where quantum classifiers are trained by using an attack-aware, adversarial…

Quantum Physics · Physics 2025-04-25 Petros Georgiou , Aaron Mark Thomas , Sharu Theresa Jose , Osvaldo Simeone

Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks…

Machine Learning · Statistics 2019-05-17 Chen Zhu , W. Ronny Huang , Ali Shafahi , Hengduo Li , Gavin Taylor , Christoph Studer , Tom Goldstein

Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack success rates over randomly selected targets, obscuring true…

Machine Learning · Computer Science 2026-05-25 William Xu , Chenyu Zhang , Yihan Wang , Matthew Y. R. Yang , Zuoqiu Liu , Gautam Kamath , Yaoliang Yu , Yiwei Lu

Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…

Machine Learning · Computer Science 2019-09-26 Luis Muñoz-González , Bjarne Pfitzner , Matteo Russo , Javier Carnerero-Cano , Emil C. Lupu

Training pipelines for machine learning (ML) based malware classification often rely on crowdsourced threat feeds, exposing a natural attack injection point. In this paper, we study the susceptibility of feature-based ML malware classifiers…

Cryptography and Security · Computer Science 2021-01-12 Giorgio Severi , Jim Meyer , Scott Coull , Alina Oprea

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Cryptography and Security · Computer Science 2022-10-21 You Guo , Jun Wang , Trevor Cohn

Generalization error bounds are critical to understanding the performance of machine learning models. In this work, building upon a new bound of the expected value of an arbitrary function of the population and empirical risk of a learning…

Information Theory · Computer Science 2021-05-07 Gholamali Aminian , Laura Toni , Miguel R. D. Rodrigues

We present a general approach to deriving bounds on the generalization error of randomized learning algorithms. Our approach can be used to obtain bounds on the average generalization error as well as bounds on its tail probabilities, both…

Information Theory · Computer Science 2020-09-10 Fredrik Hellström , Giuseppe Durisi

A recent source of concern for the security of neural networks is the emergence of clean-label dataset poisoning attacks, wherein correctly labeled poison samples are injected into the training dataset. While these poison samples look…

Machine Learning · Computer Science 2021-03-16 Hojjat Aghakhani , Dongyu Meng , Yu-Xiang Wang , Christopher Kruegel , Giovanni Vigna

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

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

As the capacity of deep neural networks (DNNs) increases, their need for huge amounts of data significantly grows. A common practice is to outsource the training process or collect more data over the Internet, which introduces the risks of…

Machine Learning · Computer Science 2023-11-14 Soroush Hashemifar , Saeed Parsa , Morteza Zakeri-Nasrabadi
‹ Prev 1 3 4 5 6 7 10 Next ›