English
Related papers

Related papers: Safety-Efficacy Trade Off: Robustness against Data…

200 papers

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

Deep neural network (DNN) classifiers are vulnerable to backdoor attacks. An adversary poisons some of the training data in such attacks by installing a trigger. The goal is to make the trained DNN output the attacker's desired class…

Machine Learning · Computer Science 2022-10-14 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

Stealthy data poisoning during fine-tuning can backdoor large language models (LLMs), threatening downstream safety. Existing detectors either use classifier-style probability signals--ill-suited to generation--or rely on rewriting, which…

Computation and Language · Computer Science 2025-11-13 Jinwen Chen , Hainan Zhang , Fei Sun , Qinnan Zhang , Sijia Wen , Ziwei Wang , Zhiming Zheng

Adversarial training instances can severely distort a model's behavior. This work investigates certified regression defenses, which provide guaranteed limits on how much a regressor's prediction may change under a poisoning attack. Our key…

Machine Learning · Computer Science 2023-01-02 Zayd Hammoudeh , Daniel Lowd

The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…

Cryptography and Security · Computer Science 2025-06-19 Wassim Bouaziz , Mathurin Videau , Nicolas Usunier , El-Mahdi El-Mhamdi

Despite recent progress in backdoor attacks, existing methods remain susceptible to post-training defenses that erase the backdoor through fine-tuning or pruning. We revisit the core objectives of backdoor attacks and derive principled…

Machine Learning · Computer Science 2026-05-29 Qiyuan Wang , Yao Li , Raymond K. W. Wong

Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems, as part of a broad goal of aligning automated decisions…

Machine Learning · Computer Science 2024-10-10 Junlin Wu , Jiongxiao Wang , Chaowei Xiao , Chenguang Wang , Ning Zhang , Yevgeniy Vorobeychik

Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor…

Machine Learning · Computer Science 2026-05-22 Aman Saxena , Jan Schuchardt , Yan Scholten , Stephan Günnemann

Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world scenarios that can amplify backdoor threats. This paper…

Cryptography and Security · Computer Science 2026-02-03 Miao Lin , Feng Yu , Rui Ning , Lusi Li , Jiawei Chen , Qian Lou , Mengxin Zheng , Chunsheng Xin , Hongyi Wu

Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection of backdoors in trained models without access to the…

Machine Learning · Computer Science 2021-03-19 Todd Huster , Emmanuel Ekwedike

Graph Neural Networks (GNNs) have demonstrated strong performance across tasks such as node classification, link prediction, and graph classification, but remain vulnerable to backdoor attacks that implant imperceptible triggers during…

Machine Learning · Computer Science 2025-12-16 Xiaobao Wang , Ruoxiao Sun , Yujun Zhang , Bingdao Feng , Dongxiao He , Luzhi Wang , Di Jin

Property inference attacks consider an adversary who has access to the trained model and tries to extract some global statistics of the training data. In this work, we study property inference in scenarios where the adversary can…

Machine Learning · Computer Science 2021-01-28 Melissa Chase , Esha Ghosh , Saeed Mahloujifar

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

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Computation and Language · Computer Science 2026-02-02 Anindya Sundar Das , Kangjie Chen , Monowar Bhuyan

Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic…

Cryptography and Security · Computer Science 2025-07-15 Yanghao Su , Jie Zhang , Yiming Li , Tianwei Zhang , Qing Guo , Weiming Zhang , Nenghai Yu , Nils Lukas , Wenbo Zhou

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

We propose a Universal Defence against backdoor attacks based on Clustering and Centroids Analysis (CCA-UD). The goal of the defence is to reveal whether a Deep Neural Network model is subject to a backdoor attack by inspecting the training…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Wei Guo , Benedetta Tondi , Mauro Barni

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

Backdoor attacks embed input-dependent malicious behavior into neural networks while preserving high clean accuracy, making them a persistent threat for deployed ML systems. At the same time, real-world deployments almost never serve…

Machine Learning · Computer Science 2025-12-09 Rohan Pandey , Eric Ye

Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to adopt third-party…

Cryptography and Security · Computer Science 2021-02-04 Tongqing Zhai , Yiming Li , Ziqi Zhang , Baoyuan Wu , Yong Jiang , Shu-Tao Xia
‹ Prev 1 8 9 10 Next ›