English
Related papers

Related papers: Data Poisoning Attack Aiming the Vulnerability of …

200 papers

One of the most concerning threats for modern AI systems is data poisoning, where the attacker injects maliciously crafted training data to corrupt the system's behavior at test time. Availability poisoning is a particularly worrisome…

Machine Learning · Computer Science 2021-03-24 Antonio Emanuele Cinà , Sebastiano Vascon , Ambra Demontis , Battista Biggio , Fabio Roli , Marcello Pelillo

We study data poisoning attacks in learning from human preferences. More specifically, we consider the problem of teaching/enforcing a target policy $\pi^\dagger$ by synthesizing preference data. We seek to understand the susceptibility of…

Machine Learning · Computer Science 2025-03-14 Andi Nika , Jonathan Nöther , Debmalya Mandal , Parameswaran Kamalaruban , Adish Singla , Goran Radanović

Adversarial attacks such as poisoning attacks have attracted the attention of many machine learning researchers. Traditionally, poisoning attacks attempt to inject adversarial training data in order to manipulate the trained model. In…

Machine Learning · Computer Science 2025-03-26 Ali Raza , Shujun Li , Kim-Phuc Tran , Ludovic Koehl , Kim Duc Tran

Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more…

Machine Learning · Computer Science 2026-05-08 Qirun Zeng , Eric He , Richard Hoffmann , Xuchuang Wang , Jinhang Zuo

Continual learning aims to sequentially learn new tasks without forgetting previous tasks' knowledge (catastrophic forgetting). One factor that can cause forgetting is the interference between the gradients on losses from different tasks.…

Computation and Language · Computer Science 2025-12-01 Xueying Bai , Jinghuan Shang , Yifan Sun , Niranjan Balasubramanian

Robust training methods typically defend against specific attack types, such as Lp attacks with fixed budgets, and rarely account for the fact that defenders may encounter new attacks over time. A natural solution is to adapt the defended…

Machine Learning · Computer Science 2025-02-07 Sihui Dai , Christian Cianfarani , Arjun Bhagoji , Vikash Sehwag , Prateek Mittal

While numerous defense methods have been proposed to prohibit potential poisoning attacks from untrusted data sources, most research works only defend against specific attacks, which leaves many avenues for an adversary to exploit. In this…

Machine Learning · Computer Science 2023-11-23 Minh-Hao Van , Alycia N. Carey , Xintao Wu

Model inversion attacks involve reconstructing the training data of a target model, which raises serious privacy concerns for machine learning models. However, these attacks, especially learning-based methods, are likely to suffer from low…

Cryptography and Security · Computer Science 2023-06-27 Shuai Zhou , Tianqing Zhu , Dayong Ye , Xin Yu , Wanlei Zhou

Contrastive learning pre-trains an image encoder using a large amount of unlabeled data such that the image encoder can be used as a general-purpose feature extractor for various downstream tasks. In this work, we propose PoisonedEncoder, a…

Cryptography and Security · Computer Science 2023-01-04 Hongbin Liu , Jinyuan Jia , Neil Zhenqiang Gong

Meta reinforcement learning (meta RL), as a combination of meta-learning ideas and reinforcement learning (RL), enables the agent to adapt to different tasks using a few samples. However, this sampling-based adaptation also makes meta RL…

Machine Learning · Computer Science 2023-03-09 Tao Li , Haozhe Lei , Quanyan Zhu

Continually learning new skills is important for intelligent systems, yet standard deep learning methods suffer from catastrophic forgetting of the past. Recent works address this with weight regularisation. Functional regularisation,…

Adversarial Machine Learning has emerged as a substantial subfield of Computer Science due to a lack of robustness in the models we train along with crowdsourcing practices that enable attackers to tamper with data. In the last two years,…

Machine Learning · Computer Science 2021-07-29 Jacob Dineen , A S M Ahsan-Ul Haque , Matthew Bielskas

Despite the growing prevalence of artificial neural networks in real-world applications, their vulnerability to adversarial attacks remains a significant concern, which motivates us to investigate the robustness of machine learning models.…

Machine Learning · Computer Science 2024-08-23 Jie Wang , Rui Gao , Yao Xie

AI-based code generators have become pivotal in assisting developers in writing software starting from natural language (NL). However, they are trained on large amounts of data, often collected from unsanitized online sources (e.g., GitHub,…

Cryptography and Security · Computer Science 2024-02-12 Domenico Cotroneo , Cristina Improta , Pietro Liguori , Roberto Natella

We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…

Cryptography and Security · Computer Science 2022-10-07 Florian Tramèr , Reza Shokri , Ayrton San Joaquin , Hoang Le , Matthew Jagielski , Sanghyun Hong , Nicholas Carlini

The increasing use of machine learning in safety-critical domains amplifies the risk of adversarial threats, especially data poisoning attacks that corrupt training data to degrade performance or induce unsafe behavior. Most existing…

Machine Learning · Computer Science 2026-05-13 Sara Taheri , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar , Majid Zamani

Nearest neighbor-based methods are commonly used for classification tasks and as subroutines of other data-analysis methods. An attacker with the capability of inserting their own data points into the training set can manipulate the…

Machine Learning · Computer Science 2022-08-16 Ara Vartanian , Will Rosenbaum , Scott Alfeld

Targeted data poisoning (TDP) aims to compromise the model's prediction on a specific (test) target by perturbing a small subset of training data. Existing work on TDP has focused on an overly ideal threat model in which the same image…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Zhizhen Chen , Zhengyu Zhao , Subrat Kishore Dutta , Chenhao Lin , Chao Shen , Xiao Zhang

The lifecycle of large language models (LLMs) is far more complex than that of traditional machine learning models, involving multiple training stages, diverse data sources, and varied inference methods. While prior research on data…

Cryptography and Security · Computer Science 2025-02-21 Pengfei He , Yue Xing , Han Xu , Zhen Xiang , Jiliang Tang

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Computation and Language · Computer Science 2024-04-04 Jiashu Xu , Mingyu Derek Ma , Fei Wang , Chaowei Xiao , Muhao Chen