相关论文: Data-Free Hard-Label Robustness Stealing Attack

Recently, the robustness of deep learning models has received widespread attention, and various methods for improving model robustness have been proposed, including adversarial training, model architecture modification, design of loss…

Device fingerprinting combined with Machine and Deep Learning (ML/DL) report promising performance when detecting cyberattacks targeting data managed by resource-constrained spectrum sensors. However, the amount of data needed to train…

Model Stealing (MS) attacks allow an adversary with black-box access to a Machine Learning model to replicate its functionality, compromising the confidentiality of the model. Such attacks train a clone model by using the predictions of the…

The popularity of Machine Learning (ML) makes the privacy of sensitive data more imperative than ever. Collaborative learning techniques like Split Learning (SL) aim to protect client data while enhancing ML processes. Though promising, SL…

Machine Learning (ML)-based detectors are becoming essential to counter the proliferation of malware. However, common ML algorithms are not designed to cope with the dynamic nature of real-world settings, where both legitimate and malicious…

Recent research demonstrates that GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. However, they mainly focus on node classification tasks, neglecting…

Previous studies have verified that the functionality of black-box models can be stolen with full probability outputs. However, under the more practical hard-label setting, we observe that existing methods suffer from catastrophic…

Deep machine learning models are increasingly deployedin the wild for providing services to users. Adversaries maysteal the knowledge of these valuable models by trainingsubstitute models according to the inference results of thetargeted…

With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has recently made great progress. However, there are few studies to examine the security of LLMs in math solving ability. Instead of attacking…

Machine Learning as a Service (MLaaS) has emerged as a widely adopted paradigm for providing access to deep neural network (DNN) models, enabling users to conveniently leverage these models through standardized APIs. However, such services…

With the increase in machine learning (ML) applications in different domains, incentives for deceiving these models have reached more than ever. As data is the core backbone of ML algorithms, attackers shifted their interest toward…

The traditional cloud-centric approach for Deep Learning (DL) requires training data to be collected and processed at a central server which is often challenging in privacy-sensitive domains like healthcare. Towards this, a new learning…

Magecart skimming attacks have emerged as a significant threat to client-side security and user trust in online payment systems. This paper addresses the challenge of achieving robust and explainable detection of Magecart attacks through a…

The wide acceptance of Internet of Things (IoT) for both household and industrial applications is accompanied by several security concerns. A major security concern is their probable abuse by adversaries towards their malicious intent.…

Federated learning (FL) has come forward as a critical approach for privacy-preserving machine learning in healthcare, allowing collaborative model training across decentralized medical datasets without exchanging clients' data. However,…

We investigate a specific security risk in FL: a group of malicious clients has impacted the model during training by disguising their identities and acting as benign clients but later switching to an adversarial role. They use their data,…

While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solution, Machine Learning as a Service (MLaaS) has emerged,…

Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model's structure, parameters, or training data. The adversary can only access the target model's…

Function-as-a-Service (FaaS) has raised a growing interest in how to "tame" serverless computing to enable domain-specific use cases such as data-intensive applications and machine learning (ML), to name a few. Recently, several systems…

Even though recent years have seen many attacks exposing severe vulnerabilities in Federated Learning (FL), a holistic understanding of what enables these attacks and how they can be mitigated effectively is still lacking. In this work, we…