activity
20222024
most citedX-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection

17 citations · 28 across the 10 of their papers we have counts for

collaborators

10 papers

cs.CV20242 cited

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

Siyuan Liang, Wei Wang, Ruoyu Chen +5

With the emergence of foundation models, deep learning-based object detectors have shown practical usability in closed set scenarios. However, for real-world tasks, object detector…

cs.CV20242 cited

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

Siyuan Liang, Kuanrong Liu, Jiajun Gong +4

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the ope…

cs.CL20241 cited

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

Xiaoxia Li, Siyuan Liang, Jiyi Zhang +3

Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where craf…

cs.CV20243 cited

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

Jiawei Liang, Siyuan Liang, Man Luo +4

Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed t…

cs.CV20243 cited

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

Jiawei Liang, Siyuan Liang, Aishan Liu +3

The proliferation of face forgery techniques has raised significant concerns within society, thereby motivating the development of face forgery detection methods. These methods aim…

cs.CR2023

Does Few-shot Learning Suffer from Backdoor Attacks?

Xinwei Liu, Xiaojun Jia, Jindong Gu +3

The field of few-shot learning (FSL) has shown promising results in scenarios where training data is limited, but its vulnerability to backdoor attacks remains largely unexplored.…