6 papers
Imperceptible and Reversible Adversarial Examples against Vision-Language Models for Privacy Protection
Qi Lu, Ziqi Zhou, Yufei Song +5
Vision Language Models (VLMs) offer powerful multimodal ability but also expose users to text-based privacy attacks where adversaries crawl online photos and query VLMs to extract…
MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training
Juntao Zhao, Qi Lu, Wei Jia +13
Modern frameworks for training large foundation models (LFMs) employ dataloaders in a data-parallel manner, with each loader processing a disjoint subset of training data. When pre…
Improving Methodologies for LLM Evaluations Across Global Languages
Akriti Vij, Benjamin Chua, Darshini Ramiah +43
As frontier AI models are deployed globally, it is essential that their behaviour remains safe and reliable across diverse linguistic and cultural contexts. To examine how current…
Improving Methodologies for Agentic Evaluations Across Domains: Leakage of Sensitive Information, Fraud and Cybersecurity Threats
Ee Wei Seah, Yongsen Zheng, Naga Nikshith +67
The rapid rise of autonomous AI systems and advancements in agent capabilities are introducing new risks due to reduced oversight of real-world interactions. Yet agent testing rema…
SegTrans: Transferable Adversarial Examples for Segmentation Models
Yufei Song, Ziqi Zhou, Qi Lu +6
Segmentation models exhibit significant vulnerability to adversarial examples in white-box settings, but existing adversarial attack methods often show poor transferability across…
When Small Guides Large: Cross-Model Co-Learning for Test-Time Adaptation
Chang'an Yi, Xiaohui Deng, Guohao Chen +3
Test-time Adaptation (TTA) adapts a given model to testing domain data with potential domain shifts through online unsupervised learning, yielding impressive performance. However,…