8 papers
Fast Test-Time Refinement for Robust Learned Image Compression
Jiaming Liang, Chi-Man Pun, Weisi Lin
Learned image compression (LIC) has demonstrated remarkable rate-distortion (RD) performance in benign settings. However, the high representational capacity endowed by deep neural…
Control Your View: High-Resolution Global Semantic Manipulation in Learned Image Compression
Jiaming Liang, Chi-Man Pun, Weisi Lin +1
Learned image compression (LIC) integrates deep neural networks (DNNs) to map high-dimensional images into compact latent representations, reducing redundancy and achieving superio…
SDDF: Specificity-Driven Dynamic Focusing for Open-Vocabulary Camouflaged Object Detection
Jiaming Liang, Yifeng Zhan, Chunlin Liu +6
Open-vocabulary object detection (OVOD) aims to detect known and unknown objects in the open world by leveraging text prompts. Benefiting from the emergence of large-scale vision--…
Fast Preemptive Robustification: High-Frequency Response Anti-Aligns Shared Vulnerability
Jiaming Liang, Chi-Man Pun
Adversarial attacks can readily compromise deep neural networks (DNNs). In particular, transferable attacks (TAs) exploit the shared vulnerabilities among DNNs, enabling perturbati…
A Unified Spatial Alignment Framework for Highly Transferable Transformation-Based Attacks on Spatially Structured Tasks
Jiaming Liang, Chi-Man Pun
Transformation-based adversarial attacks (TAAs) demonstrate strong transferability when deceiving classification models. However, existing TAAs often perform unsatisfactorily or ev…
Multilingual Safety Alignment Via Sparse Weight Editing
Jiaming Liang, Zhaoxin Wang, Handing Wang
Large Language Models (LLMs) exhibit significant safety disparities across languages, with low-resource languages (LRLs) often bypassing safety guardrails established for high-reso…
OTI: A Model-free and Visually Interpretable Measure of Image Attackability
Jiaming Liang, Haowei Liu, Chi-Man Pun
Despite the tremendous success of neural networks, benign images can be corrupted by adversarial perturbations to deceive these models. Intriguingly, images differ in their attacka…
Dynamic Parameter Optimization for Highly Transferable Transformation-Based Attacks
Jiaming Liang, Chi-Man Pun
Despite their wide application, the vulnerabilities of deep neural networks raise societal concerns. Among them, transformation-based attacks have demonstrated notable success in t…