English
Related papers

Related papers: Persistent Pre-Training Poisoning of LLMs

200 papers

Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance.…

Computation and Language · Computer Science 2026-03-19 Yongding Tao , Tian Wang , Yihong Dong , Huanyu Liu , Kechi Zhang , Xiaolong Hu , Ge 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

Large language models are pre-trained on ever-growing token budgets under the assumption that better pre-training performance translates to improved downstream models. In this work, we challenge this assumption and show that extended…

Computation and Language · Computer Science 2025-03-31 Jacob Mitchell Springer , Sachin Goyal , Kaiyue Wen , Tanishq Kumar , Xiang Yue , Sadhika Malladi , Graham Neubig , Aditi Raghunathan

Model pruning, i.e., removing a subset of model weights, has become a prominent approach to reducing the memory footprint of large language models (LLMs) during inference. Notably, popular inference engines, such as vLLM, enable users to…

Machine Learning · Computer Science 2026-04-07 Kazuki Egashira , Robin Staab , Thibaud Gloaguen , Mark Vero , Martin Vechev

Large Language Models (LLMs) have transformed the natural language processing landscape and brought to life diverse applications. Pretraining on vast web-scale data has laid the foundation for these models, yet the research community is now…

We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion requests, one often-cited potential application for unlearning…

Machine Learning · Computer Science 2026-01-16 Martin Pawelczyk , Jimmy Z. Di , Yiwei Lu , Gautam Kamath , Ayush Sekhari , Seth Neel

Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns about resilience to adversarial manipulation. This paper…

Machine Learning · Computer Science 2025-10-17 Harsh Chaudhari , Jamie Hayes , Matthew Jagielski , Ilia Shumailov , Milad Nasr , Alina Oprea

Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset also exposes the model…

Cryptography and Security · Computer Science 2023-06-06 Ziqing Yang , Xinlei He , Zheng Li , Michael Backes , Mathias Humbert , Pascal Berrang , Yang Zhang

Instruction-tuned Large Language Models designed for coding tasks are increasingly employed as AI coding assistants. However, the cybersecurity vulnerabilities and implications arising from the widespread integration of these models are not…

Cryptography and Security · Computer Science 2025-03-10 Md Imran Hossen , Sai Venkatesh Chilukoti , Liqun Shan , Sheng Chen , Yinzhi Cao , Xiali Hei

The rapid advancement of pre-trained language models (PLMs) has demonstrated promising results for various code-related tasks. However, their effectiveness in detecting real-world vulnerabilities remains a critical challenge. While existing…

Cryptography and Security · Computer Science 2025-11-25 Youpeng Li , Weiliang Qi , Xuyu Wang , Fuxun Yu , Xinda Wang

Machine learning models have achieved great success in supervised learning tasks for end-to-end training, which requires a large amount of labeled data that is not always feasible. Recently, many practitioners have shifted to…

Machine Learning · Computer Science 2024-02-21 Yiwei Lu , Matthew Y. R. Yang , Gautam Kamath , Yaoliang Yu

In the domain of large language models (LLMs), in-context learning (ICL) has been recognized for its innovative ability to adapt to new tasks, relying on examples rather than retraining or fine-tuning. This paper delves into the critical…

Cryptography and Security · Computer Science 2025-06-03 Pengfei He , Han Xu , Yue Xing , Hui Liu , Makoto Yamada , Jiliang Tang

Large language models (LLMs) are foundational explorations to artificial general intelligence, yet their alignment with human values via instruction tuning and preference learning achieves only superficial compliance. Here, we demonstrate…

Computation and Language · Computer Science 2025-06-04 Jiawei Lian , Jianhong Pan , Lefan Wang , Yi Wang , Shaohui Mei , Lap-Pui Chau

When practitioners fine-tune LLMs on unvetted datasets, an adversary can exploit the data supply chain through task-level poisoning: inserting a small number of crafted instruction-response pairs that cause the model to embed…

Cryptography and Security · Computer Science 2026-05-25 Luze Sun , Anshuman Suri , Harsh Chaudhari , Cristina Nita-Rotaru , Alina Oprea

Poisoning backdoor attacks involve an adversary manipulating the training data to induce certain behaviors in the victim model by inserting a trigger in the signal at inference time. We adapted clean label backdoor (CLBD)-data poisoning…

Cryptography and Security · Computer Science 2024-09-16 Henry Li Xinyuan , Sonal Joshi , Thomas Thebaud , Jesus Villalba , Najim Dehak , Sanjeev Khudanpur

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes available. A much more efficient solution is to continually pre-train these models, saving significant…

Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly focused on the detectable backdoor attacks. We propose a novel poisoning attack targeting the…

Cryptography and Security · Computer Science 2026-03-04 Jingyuan Xie , Wenjie Wang , Ji Wu , Jiandong Gao

Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to amplify the exposure of…

Computation and Language · Computer Science 2024-09-04 Myung Gyo Oh , Hong Eun Ahn , Leo Hyun Park , Taekyoung Kwon

Large language models (LLMs) sometimes exhibit dangerous unintended behaviors. Finding and fixing these is challenging because the attack surface is massive -- it is not tractable to exhaustively search for all possible inputs that may…

Machine Learning · Computer Science 2024-07-10 Adriano Hernandez

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
‹ Prev 1 4 5 6 7 8 10 Next ›