Related papers: Isolation and Induction: Training Robust Deep Neur…
Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query…
Membership inference attacks allow a malicious entity to predict whether a sample is used during training of a victim model or not. State-of-the-art membership inference attacks have shown to achieve good accuracy which poses a great…
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…
Deep neural networks (DNNs) have become the essential components for various commercialized machine learning services, such as Machine Learning as a Service (MLaaS). Recent studies show that machine learning services face severe privacy…
Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service API. In providing an in-depth characterization of…
As Artificial Intelligence (AI) technologies continue to gain traction in the modern-day world, they ultimately pose an immediate threat to current cybersecurity systems via exploitative methods. Prompt engineering is a relatively new field…
The distributed nature of training makes Federated Learning (FL) vulnerable to backdoor attacks, where malicious model updates aim to compromise the global model's performance on specific tasks. Existing defense methods show limited…
Gradient-based adversarial attacks subtly manipulate inputs of Machine Learning (ML) models to induce incorrect predictions. This paper investigates whether careful architectural choices alone can yield an inherently robust Deep Neural…
Recent research studies revealed that neural networks are vulnerable to adversarial attacks. State-of-the-art defensive techniques add various adversarial examples in training to improve models' adversarial robustness. However, these…
Cyber attacks constitute a significant threat to organizations with implications ranging from economic, reputational, and legal consequences. As cybercriminals' techniques get sophisticated, information security professionals face a more…
Model-sharing offers significant business value by enabling firms with well-established Machine Learning (ML) models to monetize and share their models with others who lack the resources to develop ML models from scratch. However, concerns…
We investigate the security of Split Learning -- a novel collaborative machine learning framework that enables peak performance by requiring minimal resources consumption. In the present paper, we expose vulnerabilities of the protocol and…
A common belief is that intrinsically interpretable deep learning models ensure a correct, intuitive understanding of their behavior and offer greater robustness against accidental errors or intentional manipulation. However, these beliefs…
Deep learning has gained tremendous success and great popularity in the past few years. However, deep learning systems are suffering several inherent weaknesses, which can threaten the security of learning models. Deep learning's wide use…
Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…
Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training data. To defend against MI attacks, previous work utilizes a…
Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…
Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are vulnerable to adversarial attacks, limiting their applications in security-critical systems. Recent works have shown the possibility of generating…
Graph Neural Networks (GNNs) are recognized as potent tools for processing real-world data organized in graph structures. Especially inductive GNNs, which allow for the processing of graph-structured data without relying on predefined graph…
With massive data being generated daily and the ever-increasing interconnectivity of the world's Internet infrastructures, a machine learning based intrusion detection system (IDS) has become a vital component to protect our economic and…