Related papers: Eliminating Backdoors in Neural Code Models for Se…

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…

Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g.,…

Developers increasingly construct multimodal large language models (MLLMs) by assembling pretrained components,introducing supply-chain attack surfaces.Existing security research primarily focuses on poisoning backbones such as encoders or…

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

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…

Adapting pre-trained deep learning models to customized tasks has become a popular choice for developers to cope with limited computational resources and data volume. More specifically, probing--training a downstream head on a pre-trained…

Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditional data poisoning or parameter manipulation, architectural…

Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor attacks, which inject stealthy triggers into models for…

For saving cost, many deep neural networks (DNNs) are trained on third-party datasets downloaded from internet, which enables attacker to implant backdoor into DNNs. In 2D domain, inherent structures of different image formats are similar.…

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

Optical Character Recognition (OCR) is a widely used tool to extract text from scanned documents. Today, the state-of-the-art is achieved by exploiting deep neural networks. However, the cost of this performance is paid at the price of…

Recent studies show that despite achieving high accuracy on a number of real-world applications, deep neural networks (DNNs) can be backdoored: by injecting triggered data samples into the training dataset, the adversary can mislead the…

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks have been devised…

The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during model deployment and can evade detection by conventional…

Despite the transformative impact of deep learning across multiple domains, the inherent opacity of these models has driven the development of Explainable Artificial Intelligence (XAI). Among these efforts, Concept Bottleneck Models (CBMs)…

Recently, backdoor attacks pose a new security threat to the training process of deep neural networks (DNNs). Attackers intend to inject hidden backdoors into DNNs, such that the attacked model performs well on benign samples, whereas its…

Backdoor (Trojan) attacks are an important type of adversarial exploit against deep neural networks (DNNs), wherein a test instance is (mis)classified to the attacker's target class whenever the attacker's backdoor trigger is present. In…

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…

The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasibility of backdoor attacks against LLMs. However, existing…

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…