Xiaogeng Liu

Orcid: 0009-0008-7677-2310

According to our database1, Xiaogeng Liu authored at least 16 papers between 2021 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding.
CoRR, 2024

Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Characte.
CoRR, 2024

JailBreakV-28K: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks.
CoRR, 2024

Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models.
CoRR, 2024

AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting.
CoRR, 2024

Automatic and Universal Prompt Injection Attacks against Large Language Models.
CoRR, 2024

Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models.
Proceedings of the 33rd USENIX Security Symposium, 2024

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability.
Proceedings of the IEEE Symposium on Security and Privacy, 2024

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructions.
CoRR, 2023

Why Does Little Robustness Help? Understanding Adversarial Transferability From Surrogate Training.
CoRR, 2023

PointCRT: Detecting Backdoor in 3D Point Cloud via Corruption Robustness.
Proceedings of the 31st ACM International Conference on Multimedia, 2023

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Towards Efficient Data-Centric Robust Machine Learning with Noise-based Augmentation.
CoRR, 2022

Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
AdvHash: Set-to-set Targeted Attack on Deep Hashing with One Single Adversarial Patch.
Proceedings of the MM '21: ACM Multimedia Conference, Virtual Event, China, October 20, 2021


  Loading...