Hanxun Huang

hanxunh's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper about 2 months ago

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP

Paper • 2505.05528 • Published May 8

authored 14 papers 4 months ago

LDReg: Local Dimensionality Regularized Self-Supervised Learning

Paper • 2401.10474 • Published Jan 19, 2024

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers

Paper • 2408.01705 • Published Aug 3, 2024

Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks

Paper • 2411.15210 • Published Nov 20, 2024

Detecting Backdoor Samples in Contrastive Language Image Pretraining

Paper • 2502.01385 • Published Feb 3 • 1

Normalized Loss Functions for Deep Learning with Noisy Labels

Paper • 2006.13554 • Published Jun 24, 2020

Unlearnable Examples: Making Personal Data Unexploitable

Paper • 2101.04898 • Published Jan 13, 2021

Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

Paper • 2110.03825 • Published Oct 7, 2021

Distilling Cognitive Backdoor Patterns within an Image

Paper • 2301.10908 • Published Jan 26, 2023

Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness

Paper • 2006.13726 • Published Jun 24, 2020

Safety at Scale: A Comprehensive Survey of Large Model Safety

Paper • 2502.05206 • Published Feb 2 • 1

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models

Paper • 2408.12798 • Published Aug 23, 2024

Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks

Paper • 2401.15295 • Published Jan 27, 2024

Neural Architecture Search via Combinatorial Multi-Armed Bandit

Paper • 2101.00336 • Published Jan 1, 2021

Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models

Paper • 2410.19427 • Published Oct 25, 2024