Related papers: Backdoor Learning on Sequence to Sequence Models
Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few training samples. The attacked model behaves normally on benign…
Backdoor attacks are dangerous and difficult to prevent in federated learning (FL), where training data is sourced from untrusted clients over long periods of time. These difficulties arise because: (a) defenders in FL do not have access to…
Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, significantly enhancing artistic creation and visual…
Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…
Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent studies reveal that the condensation process can be vulnerable…
Large language models (LLMs) have acquired the ability to handle longer context lengths and understand nuances in text, expanding their dialogue capabilities beyond a single utterance. A popular user-facing application of LLMs is the…
Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…
Backdoor attacks are rapidly emerging threats to deep neural networks (DNNs). In the backdoor attack scenario, attackers usually implant the backdoor into the target model by manipulating the training dataset or training process. Then, the…
Semantic communication systems, which leverage Generative AI (GAI) to transmit semantic meaning rather than raw data, are poised to revolutionize modern communications. However, they are vulnerable to backdoor attacks, a type of poisoning…
These days, deep learning models have achieved great success in multiple fields, from autonomous driving to medical diagnosis. These models have expanded the abilities of artificial intelligence by offering great solutions to complex…
Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we investigate backdoor data poisoning attack on deep neural…
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 vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to…
Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…
Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set…
Speech language models (SLMs) are systems of systems: independent components that unite to achieve a common goal. Despite their heterogeneous nature, SLMs are often studied end-to-end; how information flows through the pipeline remains…
Copy mechanisms are employed in sequence to sequence models (seq2seq) to generate reproductions of words from the input to the output. These frameworks, operating at the lexical type level, fail to provide an explicit alignment that records…
Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…
While NLP models significantly impact our lives, there are rising concerns about privacy invasion. Although federated learning enhances privacy, attackers may recover private training data by exploiting model parameters and gradients.…
Neural conversational models tend to produce generic or safe responses in different contexts, e.g., reply \textit{"Of course"} to narrative statements or \textit{"I don't know"} to questions. In this paper, we propose an end-to-end approach…