Related papers: Backdoor Vulnerabilities in Normally Trained Deep …

In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…

Federated learning security research has predominantly focused on backdoor threats from a minority of malicious clients that intentionally corrupt model updates. This paper challenges this paradigm by investigating a more pervasive and…

Deep neural networks (DNNs) are increasingly deployed in different applications to achieve state-of-the-art performance. However, they are often applied as a black box with limited understanding of what knowledge the model has learned from…

Transfer learning from pre-trained encoders has become essential in modern machine learning, enabling efficient model adaptation across diverse tasks. However, this combination of pre-training and downstream adaptation creates an expanded…

Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training data to compromise the learning algorithm, e.g., by…

Recent research shows deep neural networks are vulnerable to different types of attacks, such as adversarial attack, data poisoning attack and backdoor attack. Among them, backdoor attack is the most cunning one and can occur in almost…

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…

Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.…

Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is…

Recent studies revealed that deep learning is susceptible to backdoor poisoning attacks. An adversary can embed a hidden backdoor into a model to manipulate its predictions by only modifying a few training data, without controlling the…

We present a new type of backdoor attack that exploits a vulnerability of convolutional neural networks (CNNs) that has been previously unstudied. In particular, we examine the application of facial recognition. Deep learning techniques are…

Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing…

Deep neural networks (DNNs) are vulnerable to a class of attacks called "backdoor attacks", which create an association between a backdoor trigger and a target label the attacker is interested in exploiting. A backdoored DNN performs well…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Deep neural networks have significantly improved the performance of face forgery detection models in discriminating Artificial Intelligent Generated Content (AIGC). However, their security is significantly threatened by the injection of…

Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models.…

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Over the past few years, the emergence of backdoor attacks has presented significant challenges to deep learning systems, allowing attackers to insert backdoors into neural networks. When data with a trigger is processed by a backdoor…

Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards…

Deep neural networks (DNNs) provide excellent performance across a wide range of classification tasks, but their training requires high computational resources and is often outsourced to third parties. Recent work has shown that outsourced…