Alert button
Picture for Siyuan Liang

Siyuan Liang

Alert button

Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection

Add code
Bookmark button
Alert button
May 13, 2024
Dehong Kong, Siyuan Liang, Wenqi Ren

Viaarxiv icon

Towards Robust Physical-world Backdoor Attacks on Lane Detection

Add code
Bookmark button
Alert button
May 09, 2024
Xinwei Zhang, Aishan Liu, Tianyuan Zhang, Siyuan Liang, Xianglong Liu

Viaarxiv icon

Object Detectors in the Open Environment: Challenges, Solutions, and Outlook

Add code
Bookmark button
Alert button
Apr 09, 2024
Siyuan Liang, Wei Wang, Ruoyu Chen, Aishan Liu, Boxi Wu, Ee-Chien Chang, Xiaochun Cao, Dacheng Tao

Viaarxiv icon

Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning

Add code
Bookmark button
Alert button
Mar 24, 2024
Siyuan Liang, Kuanrong Liu, Jiajun Gong, Jiawei Liang, Yuan Xun, Ee-Chien Chang, Xiaochun Cao

Viaarxiv icon

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds

Add code
Bookmark button
Alert button
Mar 08, 2024
Tianrui Lou, Xiaojun Jia, Jindong Gu, Li Liu, Siyuan Liang, Bangyan He, Xiaochun Cao

Figure 1 for Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
Figure 2 for Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
Figure 3 for Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
Figure 4 for Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
Viaarxiv icon

Less is More: Fewer Interpretable Region via Submodular Subset Selection

Add code
Bookmark button
Alert button
Feb 29, 2024
Ruoyu Chen, Hua Zhang, Siyuan Liang, Jingzhi Li, Xiaochun Cao

Viaarxiv icon

Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs

Add code
Bookmark button
Alert button
Feb 27, 2024
Xiaoxia Li, Siyuan Liang, Jiyi Zhang, Han Fang, Aishan Liu, Ee-Chien Chang

Viaarxiv icon

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models

Add code
Bookmark button
Alert button
Feb 21, 2024
Jiawei Liang, Siyuan Liang, Man Luo, Aishan Liu, Dongchen Han, Ee-Chien Chang, Xiaochun Cao

Viaarxiv icon

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

Add code
Bookmark button
Alert button
Feb 18, 2024
Jiawei Liang, Siyuan Liang, Aishan Liu, Xiaojun Jia, Junhao Kuang, Xiaochun Cao

Viaarxiv icon

Does Few-shot Learning Suffer from Backdoor Attacks?

Add code
Bookmark button
Alert button
Dec 31, 2023
Xinwei Liu, Xiaojun Jia, Jindong Gu, Yuan Xun, Siyuan Liang, Xiaochun Cao

Figure 1 for Does Few-shot Learning Suffer from Backdoor Attacks?
Figure 2 for Does Few-shot Learning Suffer from Backdoor Attacks?
Figure 3 for Does Few-shot Learning Suffer from Backdoor Attacks?
Figure 4 for Does Few-shot Learning Suffer from Backdoor Attacks?
Viaarxiv icon