English
Related papers

Related papers: Pareto-Secure Machine Learning (PSML): Fingerprint…

200 papers

Model extraction attacks currently pose a non-negligible threat to the security and privacy of deep learning models. By querying the model with a small dataset and usingthe query results as the ground-truth labels, an adversary can steal a…

Cryptography and Security · Computer Science 2024-07-02 Huajie Chen , Tianqing Zhu , Lefeng Zhang , Bo Liu , Derui Wang , Wanlei Zhou , Minhui Xue

Deep neural networks are vulnerable to adversarial examples, which dramatically alter model output using small input changes. We propose Neural Fingerprinting, a simple, yet effective method to detect adversarial examples by verifying…

Machine Learning · Computer Science 2019-06-18 Sumanth Dathathri , Stephan Zheng , Tianwei Yin , Richard M. Murray , Yisong Yue

Machine learning has become a crucial part of our lives, with applications spanning nearly every aspect of our daily activities. However, using personal information in machine learning applications has sparked significant security and…

Cryptography and Security · Computer Science 2025-10-14 Nges Brian Njungle , Eric Jahns , Luigi Mastromauro , Edwin P. Kayang , Milan Stojkov , Michel A. Kinsy

Detecting the source model of AI-generated images is a growing accountability problem. AI fingerprinting techniques address this by detecting imperceptible patterns in the images that are unique to each model, achieving high detection…

Cryptography and Security · Computer Science 2026-05-06 Kai Yao , Marc Juarez

Recent attacks on Machine Learning (ML) models such as evasion attacks with adversarial examples and models stealing through extraction attacks pose several security and privacy threats. Prior work proposes to use adversarial training to…

Machine Learning · Computer Science 2022-08-23 Kacem Khaled , Gabriela Nicolescu , Felipe Gohring de Magalhães

Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…

Machine Learning · Computer Science 2023-09-12 Kacem Khaled , Mouna Dhaouadi , Felipe Gohring de Magalhães , Gabriela Nicolescu

Modern applications increasingly rely on inference serving systems to provide low-latency insights with a diverse set of machine learning models. Existing systems often utilize resource elasticity to scale with demand. However, many…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-13 Joel Wolfrath , Daniel Frink , Abhishek Chandra

Model fingerprinting has emerged as a promising paradigm for claiming model ownership. However, robustness evaluations of these schemes have mostly focused on benign perturbations such as incremental fine-tuning, model merging, and…

Cryptography and Security · Computer Science 2025-10-01 Anshul Nasery , Edoardo Contente , Alkin Kaz , Pramod Viswanath , Sewoong Oh

In model extraction attacks, adversaries can steal a machine learning model exposed via a public API by repeatedly querying it and adjusting their own model based on obtained predictions. To prevent model stealing, existing defenses focus…

Cryptography and Security · Computer Science 2022-12-13 Adam Dziedzic , Muhammad Ahmad Kaleem , Yu Shen Lu , Nicolas Papernot

The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an…

Cryptography and Security · Computer Science 2026-05-29 Zisis Tsiatsikas , Alexandros Fakis , Georgios Karopoulos , Vasileios Kouliaridis , Marios Anagnostopoulos

Federated Learning (FL) is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property (IP) threats. Model extraction (ME) attacks pose a significant risk to Machine Learning…

Cryptography and Security · Computer Science 2025-06-02 Sayyed Farid Ahamed , Sandip Roy , Soumya Banerjee , Marc Vucovich , Kevin Choi , Abdul Rahman , Alison Hu , Edward Bowen , Sachin Shetty

In Machine Learning as a Service, a provider trains a deep neural network and gives many users access. The hosted (source) model is susceptible to model stealing attacks, where an adversary derives a surrogate model from API access to the…

Machine Learning · Computer Science 2021-01-21 Nils Lukas , Yuxuan Zhang , Florian Kerschbaum

Deep learning has achieved tremendous success in numerous industrial applications. As training a good model often needs massive high-quality data and computation resources, the learned models often have significant business values. However,…

Multimedia · Computer Science 2020-02-26 Jie Zhang , Dongdong Chen , Jing Liao , Han Fang , Weiming Zhang , Wenbo Zhou , Hao Cui , Nenghai Yu

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

Computation and Language · Computer Science 2024-11-11 Md Abdur Rahman , Fan Wu , Alfredo Cuzzocrea , Sheikh Iqbal Ahamed

Privacy-preserving machine learning (PPML) based on cryptographic protocols has emerged as a promising paradigm to protect user data privacy in cloud-based machine learning services. While it achieves formal privacy protection, PPML often…

Cryptography and Security · Computer Science 2025-07-22 Wenxuan Zeng , Tianshi Xu , Yi Chen , Yifan Zhou , Mingzhe Zhang , Jin Tan , Cheng Hong , Meng Li

This paper investigates the resilience of a ResNet-50 image classification model under two prominent security threats: Fast Gradient Sign Method (FGSM) adversarial attacks and malicious payload injection. Initially, the model attains a…

Cryptography and Security · Computer Science 2025-01-22 Umesh Yadav , Suman Niroula , Gaurav Kumar Gupta , Bicky Yadav

A key concern for AI safety remains understudied in the machine learning (ML) literature: how can we ensure users of ML models do not leverage predictions on incorrect personal data to harm others? This is particularly pertinent given the…

Machine Learning · Computer Science 2025-10-01 Muhammad H. Ashiq , Peter Triantafillou , Hung Yun Tseng , Grigoris G. Chrysos

Machine learning (ML) is vulnerable to inference (e.g., membership inference, property inference, and data reconstruction) attacks that aim to infer the private information of training data or dataset. Existing defenses are only designed…

Machine Learning · Computer Science 2024-03-05 Sayedeh Leila Noorbakhsh , Binghui Zhang , Yuan Hong , Binghui Wang

In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: *accuracy*, i.e., performing well on the…

Machine Learning · Computer Science 2020-03-05 Matthew Jagielski , Nicholas Carlini , David Berthelot , Alex Kurakin , Nicolas Papernot

Website Fingerprinting attacks enable a passive eavesdropper to recover the user's otherwise anonymized web browsing activity by matching the observed traffic with prerecorded web traffic templates. The defenses that have been proposed to…

Cryptography and Security · Computer Science 2016-07-20 Marc Juarez , Mohsen Imani , Mike Perry , Claudia Diaz , Matthew Wright