Ee-Chien Chang

Associate Professor@National University of Singapore·新加坡·OpenReview

研究方向

Trusted Executation Environment · privacy preserving technology · Machine Learning Security · Inversion Attack · Adversarial Example · Applied Cryptography · Cloud Security · Multimedia security · biometric cryptography · watermarking

4.0

CASIAL: Geometric Distortion Robust Image Watermarking

ICLR 2026Rejected

三作

4.0

Uncovering Activation Keys in the Dark: Revealing Learned Concepts in LoRA Text-To-Image Models

ICLR 2026Rejected

通讯

4.0

Equipping LLMs with Self-Awareness for High-Stakes Tasks

ICLR 2026Rejected

3.5

Clean-Action Backdoor Attacks on Vision-Language-Action Models via Sequential Error Exploitation

ICLR 2026Withdrawn

三作

2.5

AttackSeqBench: Benchmarking Large Language Models in Analyzing Attack Sequences within Cyber Threat Intelligence

合作者 (20)

Ee-Chien Chang

CASIAL: Geometric Distortion Robust Image Watermarking

Uncovering Activation Keys in the Dark: Revealing Learned Concepts in LoRA Text-To-Image Models

Equipping LLMs with Self-Awareness for High-Stakes Tasks

Clean-Action Backdoor Attacks on Vision-Language-Action Models via Sequential Error Exploitation

AttackSeqBench: Benchmarking Large Language Models in Analyzing Attack Sequences within Cyber Threat Intelligence

Towards Lightweight Deep Watermarking Framework

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

Lightweight-Mark: Rethinking Deep Learning-Based Watermarking