Picture for Zhongliang Guo

Zhongliang Guo

MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks

Add code
Oct 17, 2024
Figure 1 for MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks
Figure 2 for MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks
Figure 3 for MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks
Figure 4 for MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks
Viaarxiv icon

Weak-To-Strong Backdoor Attacks for LLMs with Contrastive Knowledge Distillation

Add code
Sep 26, 2024
Viaarxiv icon

Instant Adversarial Purification with Adversarial Consistency Distillation

Add code
Sep 02, 2024
Viaarxiv icon

A Grey-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse

Add code
Aug 20, 2024
Viaarxiv icon

Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges

Add code
Jul 11, 2024
Viaarxiv icon

A Survey of Backdoor Attacks and Defenses on Large Language Models: Implications for Security Measures

Add code
Jun 10, 2024
Viaarxiv icon

Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack

Add code
Jan 18, 2024
Viaarxiv icon

Semi-Supervised Crowd Counting with Contextual Modeling: Facilitating Holistic Understanding of Crowd Scenes

Add code
Oct 23, 2023
Viaarxiv icon

A White-Box False Positive Adversarial Attack Method on Contrastive Loss-Based Offline Handwritten Signature Verification Models

Add code
Aug 17, 2023
Viaarxiv icon

A Bayesian algorithm for retrosynthesis

Add code
Mar 06, 2020
Figure 1 for A Bayesian algorithm for retrosynthesis
Figure 2 for A Bayesian algorithm for retrosynthesis
Figure 3 for A Bayesian algorithm for retrosynthesis
Figure 4 for A Bayesian algorithm for retrosynthesis
Viaarxiv icon