中文
相关论文

相关论文: Fake Resume Attacks: Data Poisoning on Online Job …

200 篇论文

Deep learning models are often trained on distributed, web-scale datasets crawled from the internet. In this paper, we introduce two new dataset poisoning attacks that intentionally introduce malicious examples to a model's performance. Our…

Face Recognition Systems (FRS) have increasingly integrated into critical applications, including surveillance and user authentication, highlighting their pivotal role in modern security systems. Recent studies have revealed vulnerabilities…

密码学与安全 · 计算机科学 2024-06-11 Jiahao Chen , Zhiqiang Shen , Yuwen Pu , Chunyi Zhou , Changjiang Li , Jiliang Li , Ting Wang , Shouling Ji

Can machine learning models for recommendation be easily fooled? While the question has been answered for hand-engineered fake user profiles, it has not been explored for machine learned adversarial attacks. This paper attempts to close…

信息检索 · 计算机科学 2018-09-25 Konstantina Christakopoulou , Arindam Banerjee

The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised…

密码学与安全 · 计算机科学 2024-03-11 Antonio Emanuele Cinà , Kathrin Grosse , Ambra Demontis , Battista Biggio , Fabio Roli , Marcello Pelillo

The concept of learned index structures relies on the idea that the input-output functionality of a database index can be viewed as a prediction task and, thus, be implemented using a machine learning model instead of traditional…

密码学与安全 · 计算机科学 2022-03-01 Evgenios M. Kornaropoulos , Silei Ren , Roberto Tamassia

This paper investigates the critical issue of data poisoning attacks on AI models, a growing concern in the ever-evolving landscape of artificial intelligence and cybersecurity. As advanced technology systems become increasingly prevalent…

密码学与安全 · 计算机科学 2025-03-13 Halima I. Kure , Pradipta Sarkar , Ahmed B. Ndanusa , Augustine O. Nwajana

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…

机器学习 · 计算机科学 2024-01-23 Benjamin Schneider , Nils Lukas , Florian Kerschbaum

Job search through online matching engines nowadays are very prominent and beneficial to both job seekers and employers. But the solutions of traditional engines without understanding the semantic meanings of different resumes have not kept…

计算与语言 · 计算机科学 2016-07-27 Yiou Lin , Hang Lei , Prince Clement Addo , Xiaoyu Li

Data poisoning is a training-time attack that undermines the trustworthiness of learned models. In a targeted data poisoning attack, an adversary manipulates the training dataset to alter the classification of a targeted test point. Given…

机器学习 · 计算机科学 2025-11-18 Nakshatra Gupta , Sumanth Prabhu , Supratik Chakraborty , R Venkatesh

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…

密码学与安全 · 计算机科学 2023-12-11 Shuli Jiang , Swanand Ravindra Kadhe , Yi Zhou , Ling Cai , Nathalie Baracaldo

In this work, we investigate the concept of biometric backdoors: a template poisoning attack on biometric systems that allows adversaries to stealthily and effortlessly impersonate users in the long-term by exploiting the template update…

密码学与安全 · 计算机科学 2020-11-06 Giulio Lovisotto , Simon Eberz , Ivan Martinovic

Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…

机器学习 · 计算机科学 2021-10-13 Bingyin Zhao , Yingjie Lao

A key challenge of big data analytics is how to collect a large volume of (labeled) data. Crowdsourcing aims to address this challenge via aggregating and estimating high-quality data (e.g., sentiment label for text) from pervasive…

密码学与安全 · 计算机科学 2021-02-26 Minghong Fang , Minghao Sun , Qi Li , Neil Zhenqiang Gong , Jin Tian , Jia Liu

Large amounts of incremental learning algorithms have been proposed to alleviate the catastrophic forgetting issue arises while dealing with sequential data on a time series. However, the adversarial robustness of incremental learners has…

密码学与安全 · 计算机科学 2023-05-31 Yiqi Zhong , Xianming Liu , Deming Zhai , Junjun Jiang , Xiangyang Ji

Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack success rates over randomly selected targets, obscuring true…

机器学习 · 计算机科学 2026-05-25 William Xu , Chenyu Zhang , Yihan Wang , Matthew Y. R. Yang , Zuoqiu Liu , Gautam Kamath , Yaoliang Yu , Yiwei Lu

URLs are central to a myriad of cyber-security threats, from phishing to the distribution of malware. Their inherent ease of use and familiarity is continuously abused by attackers to evade defences and deceive end-users. Seemingly…

密码学与安全 · 计算机科学 2021-08-31 Mahathir Almashor , Ejaz Ahmed , Benjamin Pick , Sharif Abuadbba , Raj Gaire , Seyit Camtepe , Surya Nepal

LLMs are vulnerable to prompt injection attacks. However, this vulnerability has been primarily demonstrated conceptually in academic studies or through a few anecdotal case studies. Its prevalence and impact in real-world LLM-based…

密码学与安全 · 计算机科学 2026-05-29 Mohan Zhang , Yuqi Jia , Zhen Tan , Steven Jiang , Neil Zhenqiang Gong , Tianlong Chen , Dawn Song

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…

密码学与安全 · 计算机科学 2025-06-09 Tingchen Fu , Mrinank Sharma , Philip Torr , Shay B. Cohen , David Krueger , Fazl Barez

Federated machine learning which enables resource constrained node devices (e.g., mobile phones and IoT devices) to learn a shared model while keeping the training data local, can provide privacy, security and economic benefits by designing…

密码学与安全 · 计算机科学 2020-04-22 Gan Sun , Yang Cong , Jiahua Dong , Qiang Wang , Ji Liu

Machine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions. Poisoning attacks against machine learning induce adversarial modification of data used by a…

机器学习 · 计算机科学 2021-05-13 Matthew Jagielski , Giorgio Severi , Niklas Pousette Harger , Alina Oprea