English
Related papers

Related papers: Defending against Model Stealing via Verifying Emb…

200 papers

Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing watermarks are easily removed when facing model stealing…

Cryptography and Security · Computer Science 2025-11-13 Yunfei Yang , Xiaojun Chen , Yuexin Xuan , Zhendong Zhao , Xin Zhao , He Li

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

Cryptography and Security · Computer Science 2025-01-08 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…

Machine Learning · Computer Science 2024-01-22 Janvi Thakkar , Giulio Zizzo , Sergio Maffeis

Model merging is a technique that combines multiple finetuned models into a single model without additional training, allowing a free-rider to cheaply inherit specialized capabilities. This study investigates methodologies to suppress…

Machine Learning · Computer Science 2025-07-01 Wei Junhao , Yu Zhe , Sakuma Jun

Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the…

Machine Learning · Computer Science 2022-03-02 Dmitrii Usynin , Daniel Rueckert , Georgios Kaissis

The potential for exploitation of AI models has increased due to the rapid advancement of Artificial Intelligence (AI) and the widespread use of platforms like Model Zoo for sharing AI models. Attackers can embed malware within AI models…

Cryptography and Security · Computer Science 2024-10-01 Daniel Gilkarov , Ran Dubin

As deep learning applications, especially programs of computer vision, are increasingly deployed in our lives, we have to think more urgently about the security of these applications.One effective way to improve the security of deep…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Xiao Tan , Jingbo Gao , Ruolin Li

Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Scott Freitas , Shang-Tse Chen , Zijie J. Wang , Duen Horng Chau

With the increasing use of machine-learning driven algorithmic judgements, it is critical to develop models that are robust to evolving or manipulated inputs. We propose an extensive analysis of model robustness against linguistic variation…

Computation and Language · Computer Science 2021-04-26 Maria Glenski , Ellyn Ayton , Robin Cosbey , Dustin Arendt , Svitlana Volkova

Machine learning models are increasingly used for software security tasks. These models are commonly trained and evaluated on large Internet-derived datasets, which often contain duplicated or highly similar samples. When such samples are…

Cryptography and Security · Computer Science 2026-02-02 Farnaz Soltaniani , Mohammad Ghafari

Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images. They encode images into rich features that are oblivious to downstream tasks. Behind their revolutionary representation…

Cryptography and Security · Computer Science 2023-03-28 Zeyang Sha , Xinlei He , Ning Yu , Michael Backes , Yang Zhang

Generative adversarial networks (GANs) have shown remarkable success in image synthesis, making GAN models themselves commercially valuable to legitimate model owners. Therefore, it is critical to technically protect the intellectual…

Cryptography and Security · Computer Science 2023-06-09 Hailong Hu , Jun Pang

Current graph neural network (GNN) model-stealing methods rely heavily on queries to the victim model, assuming no hard query limits. However, in reality, the number of allowed queries can be severely limited. In this paper, we demonstrate…

The performance of machine learning models is determined by the quality of their learned features. They should be invariant under irrelevant data variation but sensitive to task-relevant details. To visualize whether this is the case, we…

Machine Learning · Computer Science 2026-03-24 Armand Rousselot , Joran Wendebourg , Ullrich Köthe

Model extraction attacks aim to duplicate a machine learning model through query access to a target model. Early studies mainly focus on discriminative models. Despite the success, model extraction attacks against generative models are less…

Cryptography and Security · Computer Science 2021-01-07 Hailong Hu , Jun Pang

Production machine learning systems are consistently under attack by adversarial actors. Various deep learning models must be capable of accurately detecting fake or adversarial input while maintaining speed. In this work, we propose one…

Machine Learning · Computer Science 2021-06-15 Matthew Ciolino , Josh Kalin , David Noever

Large-scale pretrained models using self-supervised learning have reportedly improved the performance of speech anti-spoofing. However, the attacker side may also make use of such models. Also, since it is very expensive to train such…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-26 Aoi Ito , Shota Horiguchi

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time. Recent defenses have been shown to improve adversarial robustness by detecting anomalous deviations from…

Machine Learning · Computer Science 2020-10-20 Francesco Crecchi , Marco Melis , Angelo Sotgiu , Davide Bacciu , Battista Biggio

Large training data and expensive model tweaking are standard features of deep learning for images. As a result, data owners often utilize cloud resources to develop large-scale complex models, which raises privacy concerns. Existing…

Cryptography and Security · Computer Science 2023-01-03 Sagar Sharma , Yuechun Gu , Keke Chen

Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show…

Machine Learning · Statistics 2021-02-18 Sasi Kumar Murakonda , Reza Shokri , George Theodorakopoulos
‹ Prev 1 3 4 5 6 7 10 Next ›