Related papers: Poison as a Cure: Detecting & Neutralizing Variabl…
Recent studies have highlighted the vulnerability of deep neural networks to backdoor attacks, where models are manipulated to rely on embedded triggers within poisoned samples, despite the presence of both benign and trigger information.…
In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to…
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…
Federated learning allows multiple users to collaboratively train a shared classification model while preserving data privacy. This approach, where model updates are aggregated by a central server, was shown to be vulnerable to poisoning…
As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. In this paper, we perform the first systematic study of…
In a backdoor attack, an attacker injects corrupted examples into the training set. The goal of the attacker is to cause the final trained model to predict the attacker's desired target label when a predefined trigger is added to test…
Deep neural networks (DNNs) have demonstrated effectiveness in various fields. However, DNNs are vulnerable to backdoor attacks, which inject a unique pattern, called trigger, into the input to cause misclassification to an attack-chosen…
Together with impressive advances touching every aspect of our society, AI technology based on Deep Neural Networks (DNN) is bringing increasing security concerns. While attacks operating at test time have monopolised the initial attention…
Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a…
The various post-processing methods for deep-learning-based models, such as quantification, pruning, and fine-tuning, play an increasingly important role in artificial intelligence technology, with pre-train large models as one of the main…
Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of infected models will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Currently,…
Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…
Current backdoor defense methods are evaluated against a single attack at a time. This is unrealistic, as powerful machine learning systems are trained on large datasets scraped from the internet, which may be attacked multiple times by one…
Deep learning has become a cornerstone of modern artificial intelligence, enabling transformative applications across a wide range of domains. As the core element of deep learning, the quality and security of training data critically…
Deep neural networks (DNNs) demonstrate superior performance in various fields, including scrutiny and security. However, recent studies have shown that DNNs are vulnerable to backdoor attacks. Several defenses were proposed in the past to…
Deep Neural Network (DNN) models have vulnerabilities related to security concerns, with attackers usually employing complex hacking techniques to expose their structures. Data poisoning-enabled perturbation attacks are complex adversarial…
Modern neural networks are often trained on massive datasets that are web scraped with minimal human inspection. As a result of this insecure curation pipeline, an adversary can poison or backdoor the resulting model by uploading malicious…
Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. Provably bounding model behavior under such attacks remains…
Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the…
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…