Picture for Biao Yi

Biao Yi

Your Fixed Watermark is Fragile: Towards Semantic-Aware Watermark for EaaS Copyright Protection

Add code
Nov 14, 2024
Viaarxiv icon

Prompt-Guided Internal States for Hallucination Detection of Large Language Models

Add code
Nov 07, 2024
Viaarxiv icon

BadActs: A Universal Backdoor Defense in the Activation Space

Add code
May 18, 2024
Viaarxiv icon

Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding

Add code
Mar 08, 2022
Figure 1 for Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding
Figure 2 for Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding
Figure 3 for Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding
Figure 4 for Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding
Viaarxiv icon

Exploiting Language Model for Efficient Linguistic Steganalysis: An Empirical Study

Add code
Jul 26, 2021
Figure 1 for Exploiting Language Model for Efficient Linguistic Steganalysis: An Empirical Study
Figure 2 for Exploiting Language Model for Efficient Linguistic Steganalysis: An Empirical Study
Figure 3 for Exploiting Language Model for Efficient Linguistic Steganalysis: An Empirical Study
Figure 4 for Exploiting Language Model for Efficient Linguistic Steganalysis: An Empirical Study
Viaarxiv icon