English
Related papers

Related papers: Detecting AI Trojans Using Meta Neural Analysis

200 papers

Adversarial attacks add perturbations to the input features with the intent of changing the classification produced by a machine learning system. Small perturbations can yield adversarial examples which are misclassified despite being…

Machine Learning · Computer Science 2019-02-05 Rakshit Agrawal , Luca de Alfaro , David Helmbold

Outsourced deep neural networks have been demonstrated to suffer from patch-based trojan attacks, in which an adversary poisons the training sets to inject a backdoor in the obtained model so that regular inputs can be still labeled…

Cryptography and Security · Computer Science 2022-05-17 Ying He , Zhili Shen , Chang Xia , Jingyu Hua , Wei Tong , Sheng Zhong

Deep neural network (DNN) classifiers are vulnerable to backdoor attacks. An adversary poisons some of the training data in such attacks by installing a trigger. The goal is to make the trained DNN output the attacker's desired class…

Machine Learning · Computer Science 2022-10-14 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

In the era of Internet of Things (IoT), Malware has been proliferating exponentially over the past decade. Traditional anti-virus software are ineffective against modern complex Malware. In order to address this challenge, researchers have…

Cryptography and Security · Computer Science 2020-07-28 Abraham Peedikayil Kuruvila , Shamik Kundu , Kanad Basu

Nowadays, Deep Neural Networks (DNNs) report state-of-the-art results in many machine learning areas, including intrusion detection. Nevertheless, recent studies in computer vision have shown that DNNs can be vulnerable to adversarial…

Cryptography and Security · Computer Science 2021-04-21 Islam Debicha , Thibault Debatty , Jean-Michel Dricot , Wim Mees

Context: Software vulnerabilities pose a significant threat to modern software systems, as evidenced by the growing number of reported vulnerabilities and cyberattacks. These escalating trends underscore the urgent need for effective…

Software Engineering · Computer Science 2025-07-01 Siyu Chen , Jiongyi Yang , Xiang Chen , Menglin Zheng , Minnan Wei , Xiaolin Ju

A security threat to deep neural networks (DNN) is backdoor contamination, in which an adversary poisons the training data of a target model to inject a Trojan so that images carrying a specific trigger will always be classified into a…

Cryptography and Security · Computer Science 2020-12-11 Di Tang , XiaoFeng Wang , Haixu Tang , Kehuan Zhang

Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a…

Machine Learning · Computer Science 2021-01-05 Siyuan Cheng , Yingqi Liu , Shiqing Ma , Xiangyu Zhang

A significant threat to the recent, wide deployment of machine learning-based systems, including deep neural networks (DNNs), is adversarial learning attacks. We analyze possible test-time evasion-attack mechanisms and show that, in some…

Machine Learning · Computer Science 2018-06-29 David J. Miller , Yulia Wang , George Kesidis

In many interesting cases, the application of machine learning is hindered by data having a complicated structure stimulated by a structured file-formats like JSONs, XMLs, or ProtoBuffers, which is non-trivial to convert to a vector /…

Cryptography and Security · Computer Science 2020-02-12 Tomas Pevny , Marek Dedic

Identifying threats in a network traffic flow which is encrypted is uniquely challenging. On one hand it is extremely difficult to simply decrypt the traffic due to modern encryption algorithms. On the other hand, passing such an encrypted…

Cryptography and Security · Computer Science 2020-11-10 Syed Muhammad Kumail Raza , Juan Caballero

Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified to the attacker's target class when a backdoor pattern is…

Machine Learning · Computer Science 2023-08-08 Hang Wang , Zhen Xiang , David J. Miller , George Kesidis

In the very last years, cybersecurity attacks have increased at an unprecedented pace, becoming ever more sophisticated and costly. Their impact has involved both private/public companies and critical infrastructures. At the same time, due…

Cryptography and Security · Computer Science 2023-09-25 Filippo Sobrero , Beatrice Clavarezza , Daniele Ucci , Federica Bisio

Trojan backdoors can be injected into large language models at various stages, including pretraining, fine-tuning, and in-context learning, posing a significant threat to the model's alignment. Due to the nature of causal language modeling,…

Computation and Language · Computer Science 2025-01-22 Vedant Bhasin , Matthew Yudin , Razvan Stefanescu , Rauf Izmailov

While real-world applications of reinforcement learning are becoming popular, the security and robustness of RL systems are worthy of more attention and exploration. In particular, recent works have revealed that, in a multi-agent RL…

Machine Learning · Computer Science 2023-09-15 Junfeng Guo , Ang Li , Cong Liu

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Cryptography and Security · Computer Science 2025-01-08 Peihai Jiang , Xixiang Lyu , Yige Li , Jing Ma

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

Machine unlearning (MU) aims to remove the influence of particular data points from the learnable parameters of a trained machine learning model. This is a crucial capability in light of data privacy requirements, trustworthiness, and…

Machine Learning · Computer Science 2025-07-01 Xavier F. Cadet , Anastasia Borovykh , Mohammad Malekzadeh , Sara Ahmadi-Abhari , Hamed Haddadi

Off-the-shelf software for Command and Control is often used by attackers and legitimate pentesters looking for discretion. Among other functionalities, these tools facilitate the customization of their network traffic so it can mimic…

Cryptography and Security · Computer Science 2025-06-11 Clément Parssegny , Johan Mazel , Olivier Levillain , Pierre Chifflier

Despite providing high-performance solutions for computer vision tasks, the deep neural network (DNN) model has been proved to be extremely vulnerable to adversarial attacks. Current defense mainly focuses on the known attacks, but the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Lei Zhang , Yuhang Zhou , Yi Yang , Xinbo Gao