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