Related papers: SecureLearn -- An Attack-agnostic Defense for Mult…

Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning…

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…

Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…

Machine learning based system are increasingly being used for sensitive tasks such as security surveillance, guiding autonomous vehicle, taking investment decisions, detecting and blocking network intrusion and malware etc. However, recent…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Deep neural networks (DNNs) have proven to be quite effective in a vast array of machine learning tasks, with recent examples in cyber security and autonomous vehicles. Despite the superior performance of DNNs in these applications, it has…

Similar to other machine learning frameworks, Offline Reinforcement Learning (RL) is shown to be vulnerable to poisoning attacks, due to its reliance on externally sourced datasets, a vulnerability that is exacerbated by its sequential…

Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are…

These days, deep learning models have achieved great success in multiple fields, from autonomous driving to medical diagnosis. These models have expanded the abilities of artificial intelligence by offering great solutions to complex…

Federated Learning (FL) is a paradigm in Machine Learning (ML) that addresses data privacy, security, access rights and access to heterogeneous information issues by training a global model using distributed nodes. Despite its advantages,…

Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms…

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples which contain human-imperceptible perturbations. A series of defending methods, either proactive defence or reactive defence, have been proposed in the recent…

Recent continual learning approaches have primarily focused on mitigating catastrophic forgetting. Nevertheless, two critical areas have remained relatively unexplored: 1) evaluating the robustness of proposed methods and 2) ensuring the…

Deep neural networks are learning models having achieved state of the art performance in many fields like prediction, computer vision, language processing and so on. However, it has been shown that certain inputs exist which would not trick…

Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN…

We propose using a two-layered deployment of machine learning models to prevent adversarial attacks. The first layer determines whether the data was tampered, while the second layer solves a domain-specific problem. We explore three sets of…

At present, backdoor attacks attract attention as they do great harm to deep learning models. The adversary poisons the training data making the model being injected with a backdoor after being trained unconsciously by victims using the…

Federated Learning (FL) protects data privacy while providing a decentralized method for training models. However, because of the distributed schema, it is susceptible to adversarial clients that could alter results or sabotage model…

Machine learning is a powerful tool enabling full automation of a huge number of tasks without explicit programming. Despite recent progress of machine learning in different domains, these models have shown vulnerabilities when they are…

Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsistent and incomprehensible predictions with humans at some…