相关论文: Mitigating Backdoor Poisoning Attacks through the …

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been…

Backdoor attacks in reinforcement learning (RL) have previously employed intense attack strategies to ensure attack success. However, these methods suffer from high attack costs and increased detectability. In this work, we propose a novel…

Textual backdoor attack, as a novel attack model, has been shown to be effective in adding a backdoor to the model during training. Defending against such backdoor attacks has become urgent and important. In this paper, we propose AttDef,…

Backdoor attacks involve the injection of a limited quantity of poisoned examples containing triggers into the training dataset. During the inference stage, backdoor attacks can uphold a high level of accuracy for normal examples, yet when…

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…

As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…

Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data. The attacked model behaves normally on benign samples, whereas its prediction will be…

Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at test time. To avoid that the trainer recognises the presence of…

Due to the popularity of Artificial Intelligence (AI) techniques, we are witnessing an increasing number of backdoor injection attacks that are designed to maliciously threaten Deep Neural Networks (DNNs) causing misclassification. Although…

Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus. While defences against specific poisoning attacks do exist, they in general do not provide any guarantees, leaving them…

Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but…

Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems.…

Audio-based machine learning systems frequently use public or third-party data, which might be inaccurate. This exposes deep neural network (DNN) models trained on such data to potential data poisoning attacks. In this type of assault,…

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…

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…

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the adversary manipulates a small portion of training data such that the victim model predicts normally on the benign samples but classifies the triggered samples as the…

Federated Learning (FL) has emerged as a leading paradigm for privacy-preserving distributed machine learning, yet the distributed nature of FL introduces unique security challenges, notably the threat of backdoor attacks. Existing backdoor…

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…

The fusion of Large Language Models (LLMs) with recommender systems (RecSys) has dramatically advanced personalized recommendations and drawn extensive attention. Despite the impressive progress, the safety of LLM-based RecSys against…