相关论文: Poison Attacks against Text Datasets with Conditio…

Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications -- making it paramount to ensure the robustness of RL algorithms against adversarial attacks. In this work…

Poisoning attacks are a category of adversarial machine learning threats in which an adversary attempts to subvert the outcome of the machine learning systems by injecting crafted data into training data set, thus increasing the machine…

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset, which consists of images or image-text pairs. CL is vulnerable to data poisoning based backdoor attacks (DPBAs), in which an attacker…

We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…

Since 2014 when Szegedy et al. showed that carefully designed perturbations of the input can lead Deep Neural Networks (DNNs) to wrongly classify its label, there has been an ongoing research to make DNNs more robust to such malicious…

A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction…

Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned…

Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…

In this paper, we study PAC learnability and certification of predictions under instance-targeted poisoning attacks, where the adversary who knows the test instance may change a fraction of the training set with the goal of fooling the…

Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-time vulnerabilities extend to deep…

Backdoor poisoning attacks are a threat to machine learning models trained on large data collected from untrusted sources; these attacks enable attackers to inject malicious behavior into the model that can be triggered by specially crafted…

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…

Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception,…

Machine learning has been proven to be susceptible to carefully crafted samples, known as adversarial examples. The generation of these adversarial examples helps to make the models more robust and gives us an insight into the underlying…

We show that by controlling parts of a physical environment in which a pre-trained deep neural network (DNN) is being fine-tuned online, an adversary can launch subtle data poisoning attacks that degrade the performance of the system. While…

Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting. While most existing work studies…

Adversarial Machine Learning has emerged as a substantial subfield of Computer Science due to a lack of robustness in the models we train along with crowdsourcing practices that enable attackers to tamper with data. In the last two years,…

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Data poisoning for reinforcement learning has historically focused on general performance degradation, and targeted attacks have been successful via perturbations that involve control of the victim's policy and rewards. We introduce an…