English
Related papers

Related papers: FreeEagle: Detecting Complex Neural Trojans in Dat…

200 papers

Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, but their vulnerability to trojan or backdoor attacks poses significant security risks. This paper explores the challenges and insights gained from…

Computation and Language · Computer Science 2024-04-23 Narek Maloyan , Ekansh Verma , Bulat Nutfullin , Bislan Ashinov

Recent works found that deep neural networks (DNNs) can be fooled by adversarial examples, which are crafted by adding adversarial noise on clean inputs. The accuracy of DNNs on adversarial examples will decrease as the magnitude of the…

Cryptography and Security · Computer Science 2023-05-30 Zhanhao Hu , Jun Zhu , Bo Zhang , Xiaolin Hu

We demonstrate a backdoor attack on a deep neural network used for regression. The backdoor attack is localized based on training-set data poisoning wherein the mislabeled samples are surrounded by correctly labeled ones. We demonstrate how…

Machine Learning · Computer Science 2021-09-07 Xi Li , George Kesidis , David J. Miller , Vladimir Lucic

Backdoor attacks are a kind of emergent training-time threat to deep neural networks (DNNs). They can manipulate the output of DNNs and possess high insidiousness. In the field of natural language processing, some attack methods have been…

Computation and Language · Computer Science 2021-11-05 Fanchao Qi , Yangyi Chen , Mukai Li , Yuan Yao , Zhiyuan Liu , Maosong Sun

Due to the increasing computational demand of Deep Neural Networks (DNNs), companies and organizations have begun to outsource the training process. However, the externally trained DNNs can potentially be backdoor attacked. It is crucial to…

Machine Learning · Computer Science 2023-07-04 Lu Pang , Tao Sun , Haibin Ling , Chao Chen

Model adaptation tackles the distribution shift problem with a pre-trained model instead of raw data, which has become a popular paradigm due to its great privacy protection. Existing methods always assume adapting to a clean target domain,…

Cryptography and Security · Computer Science 2025-02-18 Lijun Sheng , Jian Liang , Ran He , Zilei Wang , Tieniu Tan

The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (DNN) models. Trigger inversion is an effective way of…

Machine Learning · Computer Science 2023-04-07 Zhenting Wang , Kai Mei , Juan Zhai , Shiqing Ma

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the adversary manipulates a small portion of training data such that the victim model predicts normally on the benign samples but classifies the triggered samples as the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Yinghua Gao , Yiming Li , Xueluan Gong , Zhifeng Li , Shu-Tao Xia , Qian Wang

Backdoor attacks present a substantial security concern for deep learning models, especially those utilized in applications critical to safety and security. These attacks manipulate model behavior by embedding a hidden trigger during the…

Machine Learning · Computer Science 2024-01-09 Yujing Jiang , Xingjun Ma , Sarah Monazam Erfani , Yige Li , James Bailey

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Cryptography and Security · Computer Science 2025-12-19 Eden Luzon , Guy Amit , Roy Weiss , Torsten Kraub , Alexandra Dmitrienko , Yisroel Mirsky

This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is based on the intuition that the feature extraction layers of…

Machine Learning · Computer Science 2023-02-24 Hao Fu , Akshaj Kumar Veldanda , Prashanth Krishnamurthy , Siddharth Garg , Farshad Khorrami

Deep reinforcement learning (DRL) is one of the most popular algorithms to realize an autonomous driving (AD) system. The key success factor of DRL is that it embraces the perception capability of deep neural networks which, however, have…

Cryptography and Security · Computer Science 2022-11-29 Yinbo Yu , Jiajia Liu

Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but…

Machine Learning · Computer Science 2022-10-18 Yuhao Zhang , Aws Albarghouthi , Loris D'Antoni

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

Cryptography and Security · Computer Science 2017-12-18 Xinyun Chen , Chang Liu , Bo Li , Kimberly Lu , Dawn Song

Large language models (LLMs) are becoming an integrated part of software development. These models are trained on large datasets for code, where it is hard to verify each data point. Therefore, a potential attack surface can be to inject…

Software Engineering · Computer Science 2023-12-12 Aftab Hussain , Md Rafiqul Islam Rabin , Toufique Ahmed , Mohammad Amin Alipour , Bowen Xu

Trojan attacks threaten deep neural networks (DNNs) by poisoning them to behave normally on most samples, yet to produce manipulated results for inputs attached with a particular trigger. Several works attempt to detect whether a given DNN…

Machine Learning · Computer Science 2022-05-25 Tianlong Chen , Zhenyu Zhang , Yihua Zhang , Shiyu Chang , Sijia Liu , Zhangyang Wang

Training machine learning models can be very expensive or even unaffordable. This may be, for example, due to data limitations, such as unavailability or being too large, or computational power limitations. Therefore, it is a common…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Mohamed E. Hussein , Sudharshan Subramaniam Janakiraman , Wael AbdAlmageed

Time Series Classification (TSC) is highly vulnerable to backdoor attacks, posing significant security threats. Existing methods primarily focus on data poisoning during the training phase, designing sophisticated triggers to improve…

Cryptography and Security · Computer Science 2025-02-04 Chang Dong , Zechao Sun , Guangdong Bai , Shuying Piao , Weitong Chen , Wei Emma Zhang

In recent years, the neural network backdoor hidden in the parameters of the federated learning model has been proved to have great security risks. Considering the characteristics of trigger generation, data poisoning and model training in…

Machine Learning · Computer Science 2024-04-23 Rong Wang , Guichen Zhou , Mingjun Gao , Yunpeng Xiao

In machine learning Trojan attacks, an adversary trains a corrupted model that obtains good performance on normal data but behaves maliciously on data samples with certain trigger patterns. Several approaches have been proposed to detect…

Artificial Intelligence · Computer Science 2020-10-02 Xiaojun Xu , Qi Wang , Huichen Li , Nikita Borisov , Carl A. Gunter , Bo Li