English
Related papers

Related papers: Concept-ROT: Poisoning Concepts in Large Language …

200 papers

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Machine Learning · Computer Science 2023-10-31 Wencong You , Zayd Hammoudeh , Daniel Lowd

Robotic manipulation policies are increasingly empowered by \textit{large language models} (LLMs) and \textit{vision-language models} (VLMs), leveraging their understanding and perception capabilities. Recently, inference-time attacks…

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning using Chain-of-Thought (CoT) prompting. However, CoT can be biased by users' instruction. In this work, we study the reasoning robustness of LLMs to…

Computation and Language · Computer Science 2024-11-11 Esther Gan , Yiran Zhao , Liying Cheng , Yancan Mao , Anirudh Goyal , Kenji Kawaguchi , Min-Yen Kan , Michael Shieh

Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks…

Machine Learning · Computer Science 2018-11-13 Ali Shafahi , W. Ronny Huang , Mahyar Najibi , Octavian Suciu , Christoph Studer , Tudor Dumitras , Tom Goldstein

The fast advancements in Large Language Models (LLMs) are driving an increasing number of applications. Together with the growing number of users, we also see an increasing number of attackers who try to outsmart these systems. They want…

Cryptography and Security · Computer Science 2024-05-31 Patrick Levi , Christoph P. Neumann

In the rapidly advancing field of artificial intelligence, the concept of Red-Teaming or Jailbreaking large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and…

Computation and Language · Computer Science 2024-05-17 Rima Hazra , Sayan Layek , Somnath Banerjee , Soujanya Poria

Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into…

Cryptography and Security · Computer Science 2023-10-31 Manli Shu , Jiongxiao Wang , Chen Zhu , Jonas Geiping , Chaowei Xiao , Tom Goldstein

Hateful meme detection aims to prevent the proliferation of hateful memes on various social media platforms. Considering its impact on social environments, this paper introduces a previously ignored but significant threat to hateful meme…

Cryptography and Security · Computer Science 2024-12-23 Ruofei Wang , Hongzhan Lin , Ziyuan Luo , Ka Chun Cheung , Simon See , Jing Ma , Renjie Wan

Language models trained on large-scale unfiltered datasets curated from the open web acquire systemic biases, prejudices, and harmful views from their training data. We present a methodology for programmatically identifying and removing…

Computation and Language · Computer Science 2021-11-30 Helen Ngo , Cooper Raterink , João G. M. Araújo , Ivan Zhang , Carol Chen , Adrien Morisot , Nicholas Frosst

With adversarial or otherwise normal prompts, existing large language models (LLM) can be pushed to generate toxic discourses. One way to reduce the risk of LLMs generating undesired discourses is to alter the training of the LLM. This can…

Computation and Language · Computer Science 2023-02-28 Meng Cao , Mehdi Fatemi , Jackie Chi Kit Cheung , Samira Shabanian

Like all software systems, the execution of deep learning models is dictated in part by logic represented as data in memory. For decades, attackers have exploited traditional software programs by manipulating this data. We propose a live…

Cryptography and Security · Computer Science 2020-05-29 Robby Costales , Chengzhi Mao , Raphael Norwitz , Bryan Kim , Junfeng Yang

Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for LLMs with large numbers of parameters or fail to fully remove the intended information without degrading performance on knowledge that…

Computation and Language · Computer Science 2025-12-25 Shariqah Hossain , Lalana Kagal

Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular community platforms now offer convenient distribution of a large…

Machine Learning · Computer Science 2024-09-02 Md Rafi Ur Rashid , Jing Liu , Toshiaki Koike-Akino , Shagufta Mehnaz , Ye Wang

This work investigates the application of Machine Unlearning (MU) for mitigating the impact of trojans embedded in conventional large language models of natural language (Text-LLMs) and large language models of code (Code-LLMs) We propose a…

Software Engineering · Computer Science 2024-08-23 Mahdi Kazemi , Aftab Hussain , Md Rafiqul Islam Rabin , Mohammad Amin Alipour , Sen Lin

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Cryptography and Security · Computer Science 2024-08-23 Jayaram Raghuram , George Kesidis , David J. Miller

Large Reasoning Models (LRMs) are designed to solve complex tasks by generating explicit reasoning traces before producing final answers. However, we reveal a critical vulnerability in LRMs -- termed Unthinking Vulnerability -- wherein the…

Computation and Language · Computer Science 2025-05-20 Zihao Zhu , Hongbao Zhang , Ruotong Wang , Ke Xu , Siwei Lyu , Baoyuan Wu

Despite the impressive capabilities of generating images, text-to-image diffusion models are susceptible to producing undesirable outputs such as NSFW content and copyrighted artworks. To address this issue, recent studies have focused on…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Tianyun Yang , Juan Cao , Chang Xu

Large Language Models (LLMs) have demonstrated exceptional capabilities across various natural language processing tasks. Due to their training on internet-sourced datasets, LLMs can sometimes generate objectionable content, necessitating…

Computation and Language · Computer Science 2024-11-15 Leyang Hu , Boran Wang

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their explicit chain-of-thought (CoT) mechanism introduces new…

Artificial Intelligence · Computer Science 2026-05-26 Jianan Li , Simeng Qin , Xiaojun Jia , Lionel Z. Wang , Tianhang Zheng , Xiaoshuang Jia , Yang Liu , Xiaochun Cao

Recently, there has been a growing interest in knowledge editing for Large Language Models (LLMs). Current approaches and evaluations merely explore the instance-level editing, while whether LLMs possess the capability to modify concepts…

Computation and Language · Computer Science 2024-10-08 Xiaohan Wang , Shengyu Mao , Ningyu Zhang , Shumin Deng , Yunzhi Yao , Yue Shen , Lei Liang , Jinjie Gu , Huajun Chen