相关论文: DUP: Detection-guided Unlearning for Backdoor Puri…

The escalating sophistication of cyberattacks has encouraged the integration of machine learning techniques in intrusion detection systems, but the rise of adversarial examples presents a significant challenge. These crafted perturbations…

Object detection has achieved promising performance on clean datasets, but how to achieve better tradeoff between the adversarial robustness and clean precision is still under-explored. Adversarial training is the mainstream method to…

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…

Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample-wise to more fine-grained sentence element-wise (e.g.,…

In recent trends, one can observe Large Language Models (LLMs) are exposed to backdoor attacks where vicious triggers added during training or model editing to elicit harmful outputs on specific input patterns while maintaining clean…

Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences to detect such attacks. However, concealed backdoors evade…

Backdoor attacks pose a significant security risk to graph learning models. Backdoors can be embedded into the target model by inserting backdoor triggers into the training dataset, causing the model to make incorrect predictions when the…

Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazardous capabilities from models and make them inaccessible to…

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the…

Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored…

Federated learning allows multiple clients to collaboratively train a global model with the assistance of a server. However, its distributed nature makes it susceptible to poisoning attacks, where malicious clients can compromise the global…

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Extensive evidence has demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks, which motivates the development of backdoor attacks detection. Most detection methods are designed to verify whether a model is…

Backdoor attacks aim to inject a backdoor into a classifier such that it predicts any input with an attacker-chosen backdoor trigger as an attacker-chosen target class. Existing backdoor attacks require either retraining the classifier with…

Despite extensive safety alignment, Large Language Models (LLMs) often fail against jailbreak attacks. While machine unlearning has emerged as a promising defense by erasing specific harmful parameters, current methods remain vulnerable to…

Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clean-label settings…

Deep neural networks have played a crucial part in many critical domains, such as autonomous driving, face recognition, and medical diagnosis. However, deep neural networks are facing security threats from backdoor attacks and can be…

Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training can be vulnerable to poisoning and backdoor attacks by one or…