1 code implementation • 16 Apr 2024 • Chanwoo Bae, Guanhong Tao, Zhuo Zhang, Xiangyu Zhang
As such, analysts often resort to text search techniques to identify existing malware reports based on the symptoms they observe, exploiting the fact that malware samples share a lot of similarity, especially those from the same origin.
1 code implementation • 25 Mar 2024 • Siyuan Cheng, Guanhong Tao, Yingqi Liu, Guangyu Shen, Shengwei An, Shiwei Feng, Xiangzhe Xu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
Backdoor attack poses a significant security threat to Deep Learning applications.
1 code implementation • 8 Feb 2024 • Guangyu Shen, Siyuan Cheng, Kaiyuan Zhang, Guanhong Tao, Shengwei An, Lu Yan, Zhuo Zhang, Shiqing Ma, Xiangyu Zhang
Large Language Models (LLMs) have become prevalent across diverse sectors, transforming human life with their extraordinary reasoning and comprehension abilities.
no code implementations • 8 Dec 2023 • Zhuo Zhang, Guangyu Shen, Guanhong Tao, Siyuan Cheng, Xiangyu Zhang
Instead, it exploits the fact that even when an LLM rejects a toxic request, a harmful response often hides deep in the output logits.
1 code implementation • 27 Nov 2023 • Shengwei An, Sheng-Yen Chou, Kaiyuan Zhang, QiuLing Xu, Guanhong Tao, Guangyu Shen, Siyuan Cheng, Shiqing Ma, Pin-Yu Chen, Tsung-Yi Ho, Xiangyu Zhang
Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training.
1 code implementation • 27 May 2023 • Weisong Sun, Yuchen Chen, Guanhong Tao, Chunrong Fang, Xiangyu Zhang, Quanjun Zhang, Bin Luo
Neural code search models are hence behind many such engines.
no code implementations • 28 Apr 2023 • Zhiyuan Cheng, Hongjun Choi, James Liang, Shiwei Feng, Guanhong Tao, Dongfang Liu, Michael Zuzak, Xiangyu Zhang
We argue that the weakest link of fusion models depends on their most vulnerable modality, and propose an attack framework that targets advanced camera-LiDAR fusion-based 3D object detection models through camera-only adversarial attacks.
1 code implementation • CVPR 2023 • Shiwei Feng, Guanhong Tao, Siyuan Cheng, Guangyu Shen, Xiangzhe Xu, Yingqi Liu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
We show the effectiveness of our method on image encoders pre-trained on ImageNet and OpenAI's CLIP 400 million image-text pairs.
1 code implementation • 31 Jan 2023 • Zhiyuan Cheng, James Liang, Guanhong Tao, Dongfang Liu, Xiangyu Zhang
We improve adversarial robustness against physical-world attacks using L0-norm-bounded perturbation in training.
no code implementations • 29 Jan 2023 • Rui Zhu, Di Tang, Siyuan Tang, Guanhong Tao, Shiqing Ma, XiaoFeng Wang, Haixu Tang
Finally, we perform both theoretical and experimental analysis, showing that the GRASP enhancement does not reduce the effectiveness of the stealthy attacks against the backdoor detection methods based on weight analysis, as well as other backdoor mitigation methods without using detection.
1 code implementation • 16 Jan 2023 • Siyuan Cheng, Guanhong Tao, Yingqi Liu, Shengwei An, Xiangzhe Xu, Shiwei Feng, Guangyu Shen, Kaiyuan Zhang, QiuLing Xu, Shiqing Ma, Xiangyu Zhang
Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks.
no code implementations • CVPR 2023 • QiuLing Xu, Guanhong Tao, Jean Honorio, Yingqi Liu, Shengwei An, Guangyu Shen, Siyuan Cheng, Xiangyu Zhang
It trains the clone model from scratch on a very small subset of samples and aims to minimize a cloning loss that denotes the differences between the activations of important neurons across the two models.
no code implementations • 29 Nov 2022 • Guanhong Tao, Zhenting Wang, Siyuan Cheng, Shiqing Ma, Shengwei An, Yingqi Liu, Guangyu Shen, Zhuo Zhang, Yunshu Mao, Xiangyu Zhang
We leverage 20 different types of injected backdoor attacks in the literature as the guidance and study their correspondences in normally trained models, which we call natural backdoor vulnerabilities.
1 code implementation • 23 Oct 2022 • Kaiyuan Zhang, Guanhong Tao, QiuLing Xu, Siyuan Cheng, Shengwei An, Yingqi Liu, Shiwei Feng, Guangyu Shen, Pin-Yu Chen, Shiqing Ma, Xiangyu Zhang
In this work, we theoretically analyze the connection among cross-entropy loss, attack success rate, and clean accuracy in this setting.
1 code implementation • 11 Jul 2022 • Zhiyuan Cheng, James Liang, Hongjun Choi, Guanhong Tao, Zhiwen Cao, Dongfang Liu, Xiangyu Zhang
Experimental results show that our method can generate stealthy, effective, and robust adversarial patches for different target objects and models and achieves more than 6 meters mean depth estimation error and 93% attack success rate (ASR) in object detection with a patch of 1/9 of the vehicle's rear area.
no code implementations • 18 Jun 2022 • Guanhong Tao, Yingqi Liu, Siyuan Cheng, Shengwei An, Zhuo Zhang, QiuLing Xu, Guangyu Shen, Xiangyu Zhang
As such, using the samples derived from our attack in adversarial training can harden a model against these backdoor vulnerabilities.
1 code implementation • 15 Jun 2022 • Weisong Sun, Chunrong Fang, Yuchen Chen, Quanjun Zhang, Guanhong Tao, Tingxu Han, Yifei Ge, Yudu You, Bin Luo
The extractive module in the framework performs a task of extractive code summarization, which takes in the code snippet and predicts important statements containing key factual details.
1 code implementation • 16 Feb 2022 • Weisong Sun, Chunrong Fang, Yuchen Chen, Guanhong Tao, Tingxu Han, Quanjun Zhang
We evaluate the effectiveness of our technique, called TranCS, on the CodeSearchNet corpus with 1, 000 queries.
no code implementations • 11 Feb 2022 • Guangyu Shen, Yingqi Liu, Guanhong Tao, QiuLing Xu, Zhuo Zhang, Shengwei An, Shiqing Ma, Xiangyu Zhang
We develop a novel optimization method for NLPbackdoor inversion.
1 code implementation • CVPR 2022 • QiuLing Xu, Guanhong Tao, Xiangyu Zhang
We propose a novel adversarial attack targeting content features in some deep layer, that is, individual neurons in the layer.
1 code implementation • CVPR 2022 • Yingqi Liu, Guangyu Shen, Guanhong Tao, Zhenting Wang, Shiqing Ma, Xiangyu Zhang
Our results on the TrojAI competition rounds 2-4, which have patch backdoors and filter backdoors, show that existing scanners may produce hundreds of false positives (i. e., clean models recognized as trojaned), while our technique removes 78-100% of them with a small increase of false negatives by 0-30%, leading to 17-41% overall accuracy improvement.
no code implementations • CVPR 2022 • Guanhong Tao, Guangyu Shen, Yingqi Liu, Shengwei An, QiuLing Xu, Shiqing Ma, Pan Li, Xiangyu Zhang
A popular trigger inversion method is by optimization.
no code implementations • 16 Mar 2021 • Yingqi Liu, Guangyu Shen, Guanhong Tao, Zhenting Wang, Shiqing Ma, Xiangyu Zhang
A prominent challenge is hence to distinguish natural features and injected backdoors.
1 code implementation • 9 Feb 2021 • Guangyu Shen, Yingqi Liu, Guanhong Tao, Shengwei An, QiuLing Xu, Siyuan Cheng, Shiqing Ma, Xiangyu Zhang
By iteratively and stochastically selecting the most promising labels for optimization with the guidance of an objective function, we substantially reduce the complexity, allowing to handle models with many classes.
no code implementations • 12 Jun 2020 • Qiu-Ling Xu, Guanhong Tao, Xiangyu Zhang
We propose a novel technique that can generate natural-looking adversarial examples by bounding the variations induced for internal activation values in some deep layer(s), through a distribution quantile bound and a polynomial barrier loss function.
1 code implementation • 26 Apr 2020 • Qiu-Ling Xu, Guanhong Tao, Siyuan Cheng, Xiangyu Zhang
We propose a new adversarial attack to Deep Neural Networks for image classification.
1 code implementation • NeurIPS 2018 • Guanhong Tao, Shiqing Ma, Yingqi Liu, Xiangyu Zhang
Results show that our technique can achieve 94% detection accuracy for 7 different kinds of attacks with 9. 91% false positives on benign inputs.