◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Hoang Thanh-Tung

Deakin University

4 papers hereh-index 5420 citations12 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author1
  • middle author1

Across the 2 of 4 papers where every author was matched, so the position is known.

fields
  • cs.LG3
  • cs.CL1
affiliations
  • Deakin University
same name
  • Hoang Thanh-Tung — 5 papers, h 2
  • Hoang Thanh-Tung — 2 papers

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20182025
most citedWicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks

1 citations · 1 across the 1 of their papers we have counts for

collaborators

4 papers

cs.CL2025

Improving LLM Unlearning Robustness via Random Perturbations

Dang Huu-Tien, Hoang Thanh-Tung, Anh Bui +3

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the…

cs.LG2024★ 1 cited

Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks

Quang H. Nguyen, Nguyen Ngoc-Hieu, The-Anh Ta +4

Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clea…

cs.LG2020

Toward a Generalization Metric for Deep Generative Models

Hoang Thanh-Tung, Truyen Tran

Measuring the generalization capacity of Deep Generative Models (DGMs) is difficult because of the curse of dimensionality. Evaluation metrics for DGMs such as Inception Score, Fré…

cs.LG2018

On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks

Hoang Thanh-Tung, Truyen Tran

In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We sh…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.