Related papers: OrderBkd: Textual backdoor attack through repositi…
Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where…
Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set…
Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the efficacy of the…
Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…
Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…
Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on…
We study backdoor poisoning attacks against image classification networks, whereby an attacker inserts a trigger into a subset of the training data, in such a way that at test time, this trigger causes the classifier to predict some target…
Due to their decentralized nature, federated learning (FL) systems have an inherent vulnerability during their training to adversarial backdoor attacks. In this type of attack, the goal of the attacker is to use poisoned updates to implant…
Backdoor attack is a powerful attack algorithm to deep learning model. Recently, GNN's vulnerability to backdoor attack has been proved especially on graph classification task. In this paper, we propose the first backdoor detection and…
Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…
Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning…
Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the same time, the attack power of an individual user is…
With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…
Backdoor attacks are a significant threat to the performance and integrity of pre-trained language models. Although such models are routinely fine-tuned for downstream NLP tasks, recent work shows they remain vulnerable to backdoor attacks…
Deep speech classification tasks, including keyword spotting and speaker verification, are vital in speech-based human-computer interaction. Recently, the security of these technologies has been revealed to be susceptible to backdoor…
Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…
With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years. A third-party model can be poisoned in…
Recently, a special type of data poisoning (DP) attack targeting Deep Neural Network (DNN) classifiers, known as a backdoor, was proposed. These attacks do not seek to degrade classification accuracy, but rather to have the classifier learn…
Extensive literature on backdoor poison attacks has studied attacks and defenses for backdoors using "digital trigger patterns." In contrast, "physical backdoors" use physical objects as triggers, have only recently been identified, and are…
Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use…