conftrace_

adversarial mechanism

3 papers

Explore in graph

Co-occurring keywords

task alignment (9) intellectual property protection (44) watermark removal (17) gradient-based attack (47) model protection (29) model watermarking (35) selective rationalization (7) complementary mechanism (1) gradient shielding (1) image-to-image model (2)

Papers

Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal CVPR 2025
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment NIPS 2024
Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control EMNLP 2019