3 citations · 8 across the 9 of their papers we have counts for
9 papers
GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models
Haibo Jin, Ruoxi Chen, Peiyan Zhang +2
The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major s…
EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models
Ruoxi Chen, Haibo Jin, Yixin Liu +3
Text-to-image diffusion models have emerged as an evolutionary for producing creative content in image synthesis. Based on the impressive generation abilities of these models, inst…
AdvCheck: Characterizing Adversarial Examples via Local Gradient Checking
Ruoxi Chen, Haibo Jin, Jinyin Chen +1
Deep neural networks (DNNs) are vulnerable to adversarial examples, which may lead to catastrophe in security-critical domains. Numerous detection methods are proposed to character…
Is Multi-Modal Necessarily Better? Robustness Evaluation of Multi-modal Fake News Detection
Jinyin Chen, Chengyu Jia, Haibin Zheng +2
The proliferation of fake news and its serious negative social influence push fake news detection methods to become necessary tools for web managers. Meanwhile, the multi-media nat…
Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization
Qinying Liu, Zilei Wang, Ruoxi Chen +1
Weakly-supervised temporal action localization (WTAL) intends to detect action instances with only weak supervision, e.g., video-level labels. The current~\textit{de facto} pipelin…
Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neurons
Haibo Jin, Ruoxi Chen, Haibin Zheng +4
Despite impressive capabilities and outstanding performance, deep neural networks (DNNs) have captured increasing public concern about their security problems, due to their frequen…
CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
Haibo Jin, Ruoxi Chen, Jinyin Chen +3
The success of deep neural networks (DNNs) in real-world applications has benefited from abundant pre-trained models. However, the backdoored pre-trained models can pose a signific…
Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence
Ruoxi Chen, Haibo Jin, Haibin Zheng +2
The vulnerabilities of deep learning models towards adversarial attacks have attracted increasing attention, especially when models are deployed in security-critical domains. Numer…
Salient Feature Extractor for Adversarial Defense on Deep Neural Networks
Jinyin Chen, Ruoxi Chen, Haibin Zheng +3
Recent years have witnessed unprecedented success achieved by deep learning models in the field of computer vision. However, their vulnerability towards carefully crafted adversari…