English
Related papers

Related papers: Train in Vain: Functionality-Preserving Poisoning …

200 papers

Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of…

Machine Learning · Computer Science 2020-02-21 Yizhen Wang , Somesh Jha , Kamalika Chaudhuri

Data poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference. A recent survey of industry practitioners found that data poisoning is the number one concern among threats ranging from model…

Machine Learning · Computer Science 2021-06-18 Avi Schwarzschild , Micah Goldblum , Arjun Gupta , John P Dickerson , Tom Goldstein

Pre-trained Language Models (PLMs) may be poisonous with backdoors or bias injected by the suspicious attacker during the fine-tuning process. A core challenge of purifying potentially poisonous PLMs is precisely finding poisonous…

Computation and Language · Computer Science 2023-05-09 Zhiyuan Zhang , Deli Chen , Hao Zhou , Fandong Meng , Jie Zhou , Xu Sun

The increasing adoption of large language models (LLMs) for code-related tasks has raised concerns about the security of their training datasets. One critical threat is dead code poisoning, where syntactically valid but functionally…

Computation and Language · Computer Science 2025-03-03 Chi-Chien Tsai , Chia-Mu Yu , Ying-Dar Lin , Yu-Sung Wu , Wei-Bin Lee

Neural networks are successfully used in a variety of applications, many of them having safety and security concerns. As a result researchers have proposed formal verification techniques for verifying neural network properties. While…

Cryptography and Security · Computer Science 2022-05-10 Youcheng Sun , Muhammad Usman , Divya Gopinath , Corina S. Păsăreanu

Data poisoning and leakage risks impede the massive deployment of federated learning in the real world. This chapter reveals the truths and pitfalls of understanding two dominating threats: {\em training data privacy intrusion} and {\em…

Machine Learning · Computer Science 2024-09-23 Wenqi Wei , Tiansheng Huang , Zachary Yahn , Anoop Singhal , Margaret Loper , Ling Liu

Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…

Cryptography and Security · Computer Science 2025-09-16 Zedian Shao , Hongbin Liu , Jaden Mu , Neil Zhenqiang Gong

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the…

Machine Learning · Computer Science 2023-10-31 Ruixiang Tang , Jiayi Yuan , Yiming Li , Zirui Liu , Rui Chen , Xia Hu

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…

Machine Learning · Computer Science 2025-11-18 Yuting Tan , Yi Huang , Zhuo Li

LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-tuning on poisoned data, even when safeguarded by moderation…

Cryptography and Security · Computer Science 2025-07-18 Dillon Bowen , Brendan Murphy , Will Cai , David Khachaturov , Adam Gleave , Kellin Pelrine

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-27 Loc Truong , Chace Jones , Brian Hutchinson , Andrew August , Brenda Praggastis , Robert Jasper , Nicole Nichols , Aaron Tuor

Federated learning combines local updates from clients to produce a global model, which is susceptible to poisoning attacks. Most previous defense strategies relied on vectors derived from projections of local updates on a Euclidean space;…

Machine Learning · Computer Science 2024-04-19 Sungwon Han , Hyeonho Song , Sungwon Park , Meeyoung Cha

Our research addresses the overlooked security concerns related to data poisoning in continual learning (CL). Data poisoning - the intentional manipulation of training data to affect the predictions of machine learning models - was recently…

Cryptography and Security · Computer Science 2025-08-12 Stanisław Pawlak , Bartłomiej Twardowski , Tomasz Trzciński , Joost van de Weijer

Data poisoning attacks are a potential threat to machine learning (ML) models, aiming to manipulate training datasets to disrupt their performance. Existing defenses are mostly designed to mitigate specific poisoning attacks or are aligned…

Cryptography and Security · Computer Science 2025-10-28 Anum Paracha , Junaid Arshad , Mohamed Ben Farah , Khalid Ismail

Federated learning (FL) is vulnerable to poisoning attacks, where adversaries corrupt the global aggregation results and cause denial-of-service (DoS). Unlike recent model poisoning attacks that optimize the amplitude of malicious…

Machine Learning · Computer Science 2024-09-27 Hangtao Zhang , Zeming Yao , Leo Yu Zhang , Shengshan Hu , Chao Chen , Alan Liew , Zhetao Li

Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks remain relatively ineffective against modern machine…

Machine Learning · Computer Science 2023-06-07 Yiwei Lu , Gautam Kamath , Yaoliang Yu

Model poisoning attacks are critical security threats to Federated Learning (FL). Existing model poisoning attacks suffer from two key limitations: 1) they achieve suboptimal effectiveness when defenses are deployed, and/or 2) they require…

Cryptography and Security · Computer Science 2025-08-14 Yueqi Xie , Minghong Fang , Neil Zhenqiang Gong

AI programming assistants have demonstrated a tendency to generate code containing basic security vulnerabilities. While developers are ultimately responsible for validating and reviewing such outputs, improving the inherent quality of…

Cryptography and Security · Computer Science 2025-11-14 Catherine Xia , Manar H. Alalfi

Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…

Software Engineering · Computer Science 2024-03-06 Aftab Hussain , Md Rafiqul Islam Rabin , Navid Ayoobi , Mohammad Amin Alipour

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…

Machine Learning · Computer Science 2021-05-13 Matthew Jagielski , Giorgio Severi , Niklas Pousette Harger , Alina Oprea