22 citations · 34 across the 11 of their papers we have counts for
11 papers
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks
Xuanli He, Qiongkai Xu, Jun Wang +2
Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's beh…
Backdoor Attack on Multilingual Machine Translation
Jun Wang, Qiongkai Xu, Xuanli He +2
While multilingual machine translation (MNMT) systems hold substantial promise, they also have security vulnerabilities. Our research highlights that MNMT systems can be susceptibl…
TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
Xuanli He, Jun Wang, Qiongkai Xu +4
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors durin…
Realistic Speech-to-Face Generation with Speech-Conditioned Latent Diffusion Model with Face Prior
Jinting Wang, Li Liu, Jun Wang +1
Speech-to-face generation is an intriguing area of research that focuses on generating realistic facial images based on a speaker's audio speech. However, state-of-the-art methods…
IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks
Xuanli He, Jun Wang, Benjamin Rubinstein +1
Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the t…
Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation
Xuanli He, Qiongkai Xu, Jun Wang +2
Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour. For instance, backdoors can be imp…
Detecting Backdoors in Deep Text Classifiers
You Guo, Jun Wang, Trevor Cohn
Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour…
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation
Jun Wang, Chang Xu, Francisco Guzman +3
Mistranslated numbers have the potential to cause serious effects, such as financial loss or medical misinformation. In this work we develop comprehensive assessments of the robust…
Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning
Jun Wang, Chang Xu, Francisco Guzman +4
Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks.…
A Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning
Chang Xu, Jun Wang, Yuqing Tang +3
As modern neural machine translation (NMT) systems have been widely deployed, their security vulnerabilities require close scrutiny. Most recently, NMT systems have been found vuln…
FedCM: A Real-time Contribution Measurement Method for Participants in Federated Learning
Boyi Liu, Bingjie Yan, Yize Zhou +2
Federated Learning (FL) creates an ecosystem for multiple agents to collaborate on building models with data privacy consideration. The method for contribution measurement of each…