English
Related papers

Related papers: Enhancing the Antidote: Improved Pointwise Certifi…

200 papers

Certified defenses against small-norm adversarial examples have received growing attention in recent years; though certified accuracies of state-of-the-art methods remain far below their non-robust counterparts, despite the fact that…

Machine Learning · Computer Science 2023-01-24 Klas Leino

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and…

Machine Learning · Computer Science 2020-11-03 Aditi Raghunathan , Jacob Steinhardt , Percy Liang

DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in…

Machine Learning · Computer Science 2022-02-23 Yinghua Gao , Dongxian Wu , Jingfeng Zhang , Guanhao Gan , Shu-Tao Xia , Gang Niu , Masashi Sugiyama

Conformal prediction provides model-agnostic and distribution-free uncertainty quantification through prediction sets that are guaranteed to include the ground truth with any user-specified probability. Yet, conformal prediction is not…

Machine Learning · Computer Science 2025-03-18 Yan Scholten , Stephan Günnemann

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…

Machine Learning · Statistics 2019-08-27 Liwei Song , Reza Shokri , Prateek Mittal

Adversarial training yields robust models against a specific threat model, e.g., $L_\infty$ adversarial examples. Typically robustness does not generalize to previously unseen threat models, e.g., other $L_p$ norms, or larger perturbations.…

Machine Learning · Computer Science 2020-07-01 David Stutz , Matthias Hein , Bernt Schiele

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Machine Learning · Computer Science 2020-10-16 Zhen Xiang , David J. Miller , George Kesidis

We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An adversary first adds a few carefully crafted points to the…

Machine Learning · Computer Science 2024-08-02 Jimmy Z. Di , Jack Douglas , Jayadev Acharya , Gautam Kamath , Ayush Sekhari

Understanding the reliability of natural language generation is critical for deploying foundation models in security-sensitive domains. While certified poisoning defenses provide provable robustness bounds for classification tasks, they are…

Machine Learning · Computer Science 2026-02-11 Mihnea Ghitu , Matthew Wicker

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained…

Machine Learning · Computer Science 2021-06-22 Liam Fowl , Micah Goldblum , Ping-yeh Chiang , Jonas Geiping , Wojtek Czaja , Tom Goldstein

The robustness of deep neural networks (DNNs) against adversarial example attacks has raised wide attention. For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate. Compared…

Machine Learning · Computer Science 2021-05-03 Jungang Yang , Liyao Xiang , Ruidong Chen , Yukun Wang , Wei Wang , Xinbing Wang

Federated learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to client-side data poisoning attacks (DPAs) and model poisoning attacks (MPAs) that degrade global model…

Cryptography and Security · Computer Science 2025-02-07 Heyi Zhang , Yule Liu , Xinlei He , Jun Wu , Tianshuo Cong , Xinyi Huang

Over the years, researchers have developed myriad attacks that exploit the ubiquity of adversarial examples, as well as defenses that aim to guard against the security vulnerabilities posed by such attacks. Of particular interest to this…

Machine Learning · Computer Science 2023-10-17 Ravi Mangal , Klas Leino , Zifan Wang , Kai Hu , Weicheng Yu , Corina Pasareanu , Anupam Datta , Matt Fredrikson

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

There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against evasion or poisoning…

Machine Learning · Statistics 2025-06-12 Pablo G. Arce , Roi Naveiro , David Ríos Insua

Adversarial data poisoning is an effective attack against machine learning and threatens model integrity by introducing poisoned data into the training dataset. So far, it has been studied mostly for classification, even though regression…

Machine Learning · Computer Science 2020-09-16 Nicolas Michael Müller , Daniel Kowatsch , Konstantin Böttinger

Discrete adversarial attacks are symbolic perturbations to a language input that preserve the output label but lead to a prediction error. While such attacks have been extensively explored for the purpose of evaluating model robustness,…

Machine Learning · Computer Science 2021-11-02 Maor Ivgi , Jonathan Berant

Machine learning algorithms, however effective, are known to be vulnerable in adversarial scenarios where a malicious user may inject manipulated instances. In this work we focus on evasion attacks, where a model is trained in a safe…

Machine Learning · Computer Science 2020-04-08 Stefano Calzavara , Claudio Lucchese , Federico Marcuzzi , Salvatore Orlando

Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: empirical defences and certified defences. Although certified…

Machine Learning · Computer Science 2023-06-13 Piersilvio De Bartolomeis , Jacob Clarysse , Amartya Sanyal , Fanny Yang

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Cryptography and Security · Computer Science 2023-12-15 Lukas Struppek , Martin B. Hentschel , Clifton Poth , Dominik Hintersdorf , Kristian Kersting