74 citations · 191 across the 29 of their papers we have counts for
30 papers
Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
Ranjie Duan, Jiexi Liu, Xiaojun Jia +27
Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, of…
Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
Xiaodan Li, Mengjie Wu, Yao Zhu +5
Large models (LMs) are powerful content generators, yet their open-ended nature can also introduce potential risks, such as generating harmful or biased content. Existing guardrail…
EasyRobust: A Comprehensive and Easy-to-use Toolkit for Robust and Generalized Vision
Xiaofeng Mao, Yuefeng Chen, Rong Zhang +3
Deep neural networks (DNNs) has shown great promise in computer vision tasks. However, machine vision achieved by DNNs cannot be as robust as human perception. Adversarial attacks…
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Shiji Zhao, Ranjie Duan, Fengxiang Wang +7
Multimodal Large Language Models (MLLMs) have achieved impressive performance and have been put into practical use in commercial applications, but they still have potential safety…
MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue
Fengxiang Wang, Ranjie Duan, Peng Xiao +9
Large Language Models (LLMs) demonstrate outstanding performance in their reservoir of knowledge and understanding capabilities, but they have also been shown to be prone to illega…
fairBERTs: Erasing Sensitive Information Through Semantic and Fairness-aware Perturbations
Jinfeng Li, Yuefeng Chen, Xiangyu Liu +3
Pre-trained language models (PLMs) have revolutionized both the natural language processing research and applications. However, stereotypical biases (e.g., gender and racial discri…
S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
Xiaohan Yuan, Jinfeng Li, Dongxia Wang +9
Generative large language models (LLMs) have revolutionized natural language processing with their transformative and emergent capabilities. However, recent evidence indicates that…
Enhancing Few-shot CLIP with Semantic-Aware Fine-Tuning
Yao Zhu, Yuefeng Chen, Wei Wang +7
Learning generalized representations from limited training samples is crucial for applying deep neural networks in low-resource scenarios. Recently, methods based on Contrastive La…
Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging
Xiaojun Jia, Yuefeng Chen, Xiaofeng Mao +5
Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often…
COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts
Xiaofeng Mao, Yuefeng Chen, Yao Zhu +4
Practical object detection application can lose its effectiveness on image inputs with natural distribution shifts. This problem leads the research community to pay more attention…
Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training
Gege Qi, Yuefeng Chen, Xiaofeng Mao +4
Developing a practically-robust automatic speech recognition (ASR) is challenging since the model should not only maintain the original performance on clean samples, but also achie…
ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing
Xiaodan Li, Yuefeng Chen, Yao Zhu +3
Recent studies have shown that higher accuracy on ImageNet usually leads to better robustness against different corruptions. Therefore, in this paper, instead of following the trad…
TransAudio: Towards the Transferable Adversarial Audio Attack via Learning Contextualized Perturbations
Qi Gege, Yuefeng Chen, Xiaofeng Mao +5
In a transfer-based attack against Automatic Speech Recognition (ASR) systems, attacks are unable to access the architecture and parameters of the target model. Existing attack met…
Information-containing Adversarial Perturbation for Combating Facial Manipulation Systems
Yao Zhu, Yuefeng Chen, Xiaodan Li +4
With the development of deep learning technology, the facial manipulation system has become powerful and easy to use. Such systems can modify the attributes of the given facial ima…
A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking
Chang Liu, Yinpeng Dong, Wenzhao Xiang +7
The robustness of deep neural networks is usually lacking under adversarial examples, common corruptions, and distribution shifts, which becomes an important research problem in th…
Rethinking Out-of-Distribution Detection From a Human-Centric Perspective
Yao Zhu, Yuefeng Chen, Xiaodan Li +6
Out-Of-Distribution (OOD) detection has received broad attention over the years, aiming to ensure the reliability and safety of deep neural networks (DNNs) in real-world scenarios…
Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspective
Yao Zhu, Yuefeng Chen, Xiaodan Li +6
Transferable adversarial attacks against Deep neural networks (DNNs) have received broad attention in recent years. An adversarial example can be crafted by a surrogate model and t…
Enhance the Visual Representation via Discrete Adversarial Training
Xiaofeng Mao, Yuefeng Chen, Ranjie Duan +6
Adversarial Training (AT), which is commonly accepted as one of the most effective approaches defending against adversarial examples, can largely harm the standard performance, thu…
D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention
Junyu Lin, Xiaofeng Mao, Yuefeng Chen +3
DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing. However, it suffers from problems such as low performance and slow con…
Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains
Qilong Zhang, Xiaodan Li, Yuefeng Chen +4
Adversarial examples have posed a severe threat to deep neural networks due to their transferable nature. Currently, various works have paid great efforts to enhance the cross-mode…
Unrestricted Adversarial Attacks on ImageNet Competition
Yuefeng Chen, Xiaofeng Mao, Yuan He +34
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-wo…
Adversarial Attacks on ML Defense Models Competition
Yinpeng Dong, Qi-An Fu, Xiao Yang +25
Due to the vulnerability of deep neural networks (DNNs) to adversarial examples, a large number of defense techniques have been proposed to alleviate this problem in recent years.…
AdvDrop: Adversarial Attack to DNNs by Dropping Information
Ranjie Duan, Yuefeng Chen, Dantong Niu +3
Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e.g. cartoon. However, in terms of visual perception of Deep N…
Towards Robust Vision Transformer
Xiaofeng Mao, Gege Qi, Yuefeng Chen +5
Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most…