Related papers: Mudjacking: Patching Backdoor Vulnerabilities in F…

Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been proposed to mitigate these attacks, the heterogeneous…

Foundation models are at the forefront of AI research, appealing for their ability to learn from vast datasets and cater to diverse tasks. Yet, their significant computational demands raise issues of environmental impact and the risk of…

Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. However, the decentralized nature of FL also opens vulnerabilities…

Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Existing defenses are mainly built upon the observation that the…

Deep learning-based techniques have achieved state-of-the-art performance on a wide variety of recognition and classification tasks. However, these networks are typically computationally expensive to train, requiring weeks of computation on…

Backdoor attacks pose a severe threat to deep learning, yet their impact on object detection remains poorly understood compared to image classification. While attacks have been proposed, we identify critical weaknesses in existing…

If the authors of a recent Stanford report (Bommasani et al., 2021) on the opportunities and risks of "foundation models" are to be believed, these models represent a paradigm shift for AI and for the domains in which they will supposedly…

Federated learning enables training high-utility models across several clients without directly sharing their private data. As a downside, the federated setting makes the model vulnerable to various adversarial attacks in the presence of…

Many modern software projects evolve rapidly to incorporate new features and security patches. It is important for users to update their dependencies to safer versions, but many still use older, vulnerable package versions because upgrading…

Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a…

Malware classifiers are subject to training-time exploitation due to the need to regularly retrain using samples collected from the wild. Recent work has demonstrated the feasibility of backdoor attacks against malware classifiers, and yet…

Attack vectors that compromise machine learning pipelines in the physical world have been demonstrated in recent research, from perturbations to architectural components. Building on this work, we illustrate the self-obfuscation attack:…

In recent years, machine learning models have been shown to be vulnerable to backdoor attacks. Under such attacks, an adversary embeds a stealthy backdoor into the trained model such that the compromised models will behave normally on clean…

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that…

In this report we investigate fundamental requirements for the application of classifier patching on neural networks. Neural network patching is an approach for adapting neural network models to handle concept drift in nonstationary…

Institutions with limited data and computing resources often outsource model training to third-party providers in a semi-honest setting, assuming adherence to prescribed training protocols with pre-defined learning paradigm (e.g.,…

Prototype-based federated learning (PFL) has emerged as a promising paradigm to address data heterogeneity problems in federated learning, as it leverages mean feature vectors as prototypes to enhance model generalization. However, its…

Model Inversion (MI) attacks pose a significant threat to the privacy of Deep Neural Networks by recovering training data distribution from well-trained models. While existing defenses often rely on regularization techniques to reduce…

Advances in foundation modeling have reshaped computational pathology. However, the increasing number of available models and lack of standardized benchmarks make it increasingly complex to assess their strengths, limitations, and potential…

Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack…