139 citations · 492 across the 39 of their papers we have counts for
40 papers
Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?
Xiaoxiao Sun, Nidham Gazagnadou, Vivek Sharma +3
Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction attacks. Under these metrics, reconstructed images…
FROD: Robust Object Detection for Free
Muhammad, Awais, Weiming +5
Object detection is a vital task in computer vision and has become an integral component of numerous critical systems. However, state-of-the-art object detectors, similar to their…
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
Junyuan Hong, Yi Zeng, Shuyang Yu +3
Data-free knowledge distillation (KD) helps transfer knowledge from a pre-trained model (known as the teacher model) to a smaller model (known as the student model) without access…
Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark
Wenjun Peng, Jingwei Yi, Fangzhao Wu +7
Large language models (LLMs) have demonstrated powerful capabilities in both text understanding and generation. Companies have begun to offer Embedding as a Service (EaaS) based on…
Pushing the Limits of ChatGPT on NLP Tasks
Xiaofei Sun, Linfeng Dong, Xiaoya Li +8
Despite the success of ChatGPT, its performances on most NLP tasks are still well below the supervised baselines. In this work, we looked into the causes, and discovered that its s…
Alteration-free and Model-agnostic Origin Attribution of Generated Images
Zhenting Wang, Chen Chen, Yi Zeng +2
Recently, there has been a growing attention in image generation models. However, concerns have emerged regarding potential misuse and intellectual property (IP) infringement assoc…
Reconstructive Neuron Pruning for Backdoor Defense
Yige Li, Xixiang Lyu, Xingjun Ma +4
Deep neural networks (DNNs) have been found to be vulnerable to backdoor attacks, raising security concerns about their deployment in mission-critical applications. While existing…
Towards Adversarially Robust Continual Learning
Tao Bai, Chen Chen, Lingjuan Lyu +2
Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual…
Backdoor Attacks with Input-unique Triggers in NLP
Xukun Zhou, Jiwei Li, Tianwei Zhang +3
Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable…
A Pathway Towards Responsible AI Generated Content
Chen Chen, Jie Fu, Lingjuan Lyu
AI Generated Content (AIGC) has received tremendous attention within the past few years, with content generated in the format of image, text, audio, video, etc. Meanwhile, AIGC has…
On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space
Yuyang Deng, Nidham Gazagnadou, Junyuan Hong +2
Recent studies demonstrated that the adversarially robust learning under attack is harder to generalize to different domains than standard domain adaptation. How to t…
InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation
Jiahua Dong, Yang Cong, Gan Sun +4
3D object recognition has successfully become an appealing research topic in the real-world. However, most existing recognition models unreasonably assume that the categories of 3D…
Delving into the Adversarial Robustness of Federated Learning
Jie Zhang, Bo Li, Chen Chen +4
In Federated Learning (FL), models are as fragile as centrally trained models against adversarial examples. However, the adversarial robustness of federated learning remains largel…
ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms
Minzhou Pan, Yi Zeng, Lingjuan Lyu +2
Backdoor data detection is traditionally studied in an end-to-end supervised learning (SL) setting. However, recent years have seen the proliferating adoption of self-supervised le…
The Perils of Learning From Unlabeled Data: Backdoor Attacks on Semi-supervised Learning
Virat Shejwalkar, Lingjuan Lyu, Amir Houmansadr
Semi-supervised machine learning (SSL) is gaining popularity as it reduces the cost of training ML models. It does so by using very small amounts of (expensive, well-inspected) lab…
Extracted BERT Model Leaks More Information than You Think!
Xuanli He, Chen Chen, Lingjuan Lyu +1
The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing…
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
Zhiyuan Zhang, Lingjuan Lyu, Xingjun Ma +2
Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a larg…
How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?
Yi Zeng, Minzhou Pan, Himanshu Jahagirdar +3
Given the volume of data needed to train modern machine learning models, external suppliers are increasingly used. However, incorporating external data poses data poisoning risks,…
RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
Qucheng Peng, Zhengming Ding, Lingjuan Lyu +2
Source-Free domain adaptation transits the source-trained model towards target domain without exposing the source data, trying to dispel these concerns about data privacy and secur…
Turning a Curse into a Blessing: Enabling In-Distribution-Data-Free Backdoor Removal via Stabilized Model Inversion
Si Chen, Yi Zeng, Jiachen T. Wang +5
Many backdoor removal techniques in machine learning models require clean in-distribution data, which may not always be available due to proprietary datasets. Model inversion techn…
CalFAT: Calibrated Federated Adversarial Training with Label Skewness
Chen Chen, Yuchen Liu, Xingjun Ma +1
Recent studies have shown that, like traditional machine learning, federated learning (FL) is also vulnerable to adversarial attacks. To improve the adversarial robustness of FL, f…
IDEAL: Query-Efficient Data-Free Learning from Black-box Models
Jie Zhang, Chen Chen, Lingjuan Lyu
Knowledge Distillation (KD) is a typical method for training a lightweight student model with the help of a well-trained teacher model. However, most KD methods require access to e…
Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information
Yi Zeng, Minzhou Pan, Hoang Anh Just +3
Backdoor attacks insert malicious data into a training set so that, during inference time, it misclassifies inputs that have been patched with a backdoor trigger as the malware spe…
Threats to Pre-trained Language Models: Survey and Taxonomy
Shangwei Guo, Chunlong Xie, Jiwei Li +2
Pre-trained language models (PTLMs) have achieved great success and remarkable performance over a wide range of natural language processing (NLP) tasks. However, there are also gro…