English
Related papers

Related papers: Detecting Stealthy Data Poisoning Attacks in AI Co…

200 papers

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Computation and Language · Computer Science 2025-10-10 Sanhanat Sivapiromrat , Caiqi Zhang , Marco Basaldella , Nigel Collier

Learned index structures achieve high performance by modeling the cumulative distribution function (CDF) of keys, but this reliance on data distributions introduces potential vulnerability to adversarial manipulation. Prior work has…

Cryptography and Security · Computer Science 2026-04-29 Allen Jue

As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy…

Machine Learning · Computer Science 2021-04-02 Micah Goldblum , Dimitris Tsipras , Chulin Xie , Xinyun Chen , Avi Schwarzschild , Dawn Song , Aleksander Madry , Bo Li , Tom Goldstein

Automated detection of software vulnerabilities is a fundamental problem in software security. Existing program analysis techniques either suffer from high false positives or false negatives. Recent progress in Deep Learning (DL) has…

Software Engineering · Computer Science 2020-09-16 Saikat Chakraborty , Rahul Krishna , Yangruibo Ding , Baishakhi Ray

Deep learning (DL) offers potential improvements throughout the CAD tool-flow, one promising application being lithographic hotspot detection. However, DL techniques have been shown to be especially vulnerable to inference and training time…

Machine Learning · Computer Science 2020-04-28 Kang Liu , Benjamin Tan , Gaurav Rajavendra Reddy , Siddharth Garg , Yiorgos Makris , Ramesh Karri

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Cryptography and Security · Computer Science 2024-10-16 Shaokui Wei , Hongyuan Zha , Baoyuan Wu

The pervasive nature of software vulnerabilities has emerged as a primary factor for the surge in cyberattacks. Traditional vulnerability detection methods, including rule-based, signature-based, manual review, static, and dynamic analysis,…

Software Engineering · Computer Science 2025-03-07 Md Nizam Uddin , Yihe Zhang , Xiali Hei

We study indiscriminate poisoning for linear learners where an adversary injects a few crafted examples into the training data with the goal of forcing the induced model to incur higher test error. Inspired by the observation that linear…

Machine Learning · Computer Science 2023-11-13 Fnu Suya , Xiao Zhang , Yuan Tian , David Evans

Data poisoning attacks pose significant threats to machine learning models by introducing malicious data into the training process, thereby degrading model performance or manipulating predictions. Detecting and sifting out poisoned data is…

Cryptography and Security · Computer Science 2025-07-10 Haoqi He , Xiaokai Lin , Jiancai Chen , Yan Xiao

Deep neural networks (DNNs) have long been recognized as vulnerable to backdoor attacks. By providing poisoned training data in the fine-tuning process, the attacker can implant a backdoor into the victim model. This enables input samples…

Cryptography and Security · Computer Science 2024-09-10 Abdullah Arafat Miah , Yu Bi

Poisoning attacks, in which an attacker adversarially manipulates the training dataset of a machine learning (ML) model, pose a significant threat to ML security. Beta Poisoning is a recently proposed poisoning attack that disrupts model…

Cryptography and Security · Computer Science 2025-08-05 Nilufer Gulciftci , M. Emre Gursoy

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Machine Learning · Computer Science 2020-10-16 Zhen Xiang , David J. Miller , George Kesidis

Interest in poisoning attacks and backdoors recently resurfaced for Deep Learning (DL) applications. Several successful defense mechanisms have been recently proposed for Convolutional Neural Networks (CNNs), for example in the context of…

Cryptography and Security · Computer Science 2020-04-07 Maximilian Bachl , Alexander Hartl , Joachim Fabini , Tanja Zseby

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the…

Machine Learning · Computer Science 2020-08-13 Vale Tolpegin , Stacey Truex , Mehmet Emre Gursoy , Ling Liu

Natural language processing (NLP) models are known to be vulnerable to backdoor attacks, which poses a newly arisen threat to NLP models. Prior online backdoor defense methods for NLP models only focus on the anomalies at either the input…

Computation and Language · Computer Science 2022-10-17 Sishuo Chen , Wenkai Yang , Zhiyuan Zhang , Xiaohan Bi , Xu Sun

Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…

Machine Learning · Computer Science 2021-03-31 Akshay Mehra , Bhavya Kailkhura , Pin-Yu Chen , Jihun Hamm

Effective detection of energy theft can prevent revenue losses of utility companies and is also important for smart grid security. In recent years, enabled by the massive fine-grained smart meter data, deep learning (DL) approaches are…

Cryptography and Security · Computer Science 2020-10-20 Jiangnan Li , Yingyuan Yang , Jinyuan Stella Sun

The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative…

The distributed nature of local differential privacy (LDP) invites data poisoning attacks and poses unforeseen threats to the underlying LDP-supported applications. In this paper, we propose a comprehensive mitigation framework for popular…

Cryptography and Security · Computer Science 2025-06-18 Xiaolin Li , Ninghui Li , Boyang Wang , Wenhai Sun

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Computation and Language · Computer Science 2023-11-30 Jiaxin Wen , Pei Ke , Hao Sun , Zhexin Zhang , Chengfei Li , Jinfeng Bai , Minlie Huang