相关论文: Token-Level Generalization in LoRA Adapter Backdoo…

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…

Graph Foundation Models (GFMs) are pre-trained on diverse source domains and adapted to unseen targets, enabling broad generalization for graph machine learning. Despite that GFMs have attracted considerable attention recently, their…

In this paper, we introduce a novel technique for content safety and prompt injection classification for Large Language Models. Our technique, Layer Enhanced Classification (LEC), trains a Penalized Logistic Regression (PLR) classifier on…

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

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…

Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks are poorly understood. We find that existing backdoor attacks…

As the capacity of deep neural networks (DNNs) increases, their need for huge amounts of data significantly grows. A common practice is to outsource the training process or collect more data over the Internet, which introduces the risks of…

Federated Learning (FL) exposes vulnerabilities to targeted poisoning attacks that aim to cause misclassification specifically from the source class to the target class. However, using well-established defense frameworks, the poisoning…

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose…

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model. The modified training samples…

Instruction-tuned Large Language Models designed for coding tasks are increasingly employed as AI coding assistants. However, the cybersecurity vulnerabilities and implications arising from the widespread integration of these models are not…

Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly…

Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released language models. As a countermeasure, backdoor detection methods…

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…

As Large Language Models (LLMs) gain traction across critical domains, ensuring secure and trustworthy training processes has become a major concern. Backdoor attacks, where malicious actors inject hidden triggers into training data, are…

While convolutional neural networks (CNNs) have achieved success in computer vision tasks, it is vulnerable to backdoor attacks. Such attacks could mislead the victim model to make attacker-chosen prediction with a specific trigger pattern.…

Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic…

We propose a Universal Defence against backdoor attacks based on Clustering and Centroids Analysis (CCA-UD). The goal of the defence is to reveal whether a Deep Neural Network model is subject to a backdoor attack by inspecting the training…

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…