English
Related papers

Related papers: Purifying Generative LLMs from Backdoors without P…

200 papers

Large language models (LLMs) are commonly treated as stateless: once an interaction ends, no information is assumed to persist unless it is explicitly stored and re-supplied. We challenge this assumption by introducing implicit memory-the…

Machine Learning · Computer Science 2026-02-10 Ahmed Salem , Andrew Paverd , Sahar Abdelnabi

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…

We study behavioral self-awareness -- an LLM's ability to articulate its behaviors without requiring in-context examples. We finetune LLMs on datasets that exhibit particular behaviors, such as (a) making high-risk economic decisions, and…

Computation and Language · Computer Science 2025-01-22 Jan Betley , Xuchan Bao , Martín Soto , Anna Sztyber-Betley , James Chua , Owain Evans

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick…

Computation and Language · Computer Science 2021-09-29 Shaofeng Li , Hui Liu , Tian Dong , Benjamin Zi Hao Zhao , Minhui Xue , Haojin Zhu , Jialiang Lu

This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as \textit{LLM unlearning}. LLM unlearning offers a principled approach to removing the influence of undesirable data…

Computation and Language · Computer Science 2025-06-03 Jiahui Geng , Qing Li , Herbert Woisetschlaeger , Zongxiong Chen , Fengyu Cai , Yuxia Wang , Preslav Nakov , Hans-Arno Jacobsen , Fakhri Karray

Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats,…

Cryptography and Security · Computer Science 2024-06-21 Jiongxiao Wang , Jiazhao Li , Yiquan Li , Xiangyu Qi , Junjie Hu , Yixuan Li , Patrick McDaniel , Muhao Chen , Bo Li , Chaowei Xiao

Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…

Cryptography and Security · Computer Science 2025-09-24 Yuan Ma , Jiankang Wei , Yilun Lyu , Kehao Chen , Jingtong Huang

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

Machine Learning · Computer Science 2026-01-08 Arpad Berta , Gabor Danner , Istvan Hegedus , Mark Jelasity

In recent years, large language models (LLMs) have made significant progress in the field of code generation. However, as more and more users rely on these models for software development, the security risks associated with code generation…

Artificial Intelligence · Computer Science 2024-08-21 Shangxi Wu , Jitao Sang

The aligned Large Language Models (LLMs) are powerful language understanding and decision-making tools that are created through extensive alignment with human feedback. However, these large models remain susceptible to jailbreak attacks,…

Computation and Language · Computer Science 2024-03-22 Xiaogeng Liu , Nan Xu , Muhao Chen , Chaowei Xiao

Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same mechanism -- the conditional activation of specific behaviors through input triggers -- can…

Cryptography and Security · Computer Science 2026-03-10 Yige Li , Wei Zhao , Zhe Li , Nay Myat Min , Hanxun Huang , Yunhan Zhao , Xingjun Ma , Yu-Gang Jiang , Jun Sun

Recent advancements in Large Language Models (LLMs) have significantly improved their capabilities in natural language processing and code synthesis, enabling more complex applications across different fields. This paper explores the…

Cryptography and Security · Computer Science 2024-10-30 Mohammad Setak , Pooria Madani

Large Language Models (LLMs) have become powerful tools for automated code generation. However, these models often overlook critical security practices, which can result in the generation of insecure code that contains…

Software Engineering · Computer Science 2025-07-01 Hao Yan , Swapneel Suhas Vaidya , Xiaokuan Zhang , Ziyu Yao

As Large Language Models (LLMs) become increasingly integrated into software development workflows, they also become prime targets for adversarial attacks. Among these, backdoor attacks are a significant threat, allowing attackers to…

Software Engineering · Computer Science 2025-10-17 Quoc Hung Le , Thanh Le-Cong , Bach Le , Bowen Xu

Despite the advanced capabilities of contemporary machine learning (ML) models, they remain vulnerable to adversarial and backdoor attacks. This vulnerability is particularly concerning in real-world deployments, where compromised models…

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…

Computation and Language · Computer Science 2023-01-26 Jiali Wei , Ming Fan , Wenjing Jiao , Wuxia Jin , Ting Liu

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to…

Computation and Language · Computer Science 2025-04-22 Zhengxian Wu , Juan Wen , Wanli Peng , Ziwei Zhang , Yinghan Zhou , Yiming Xue

With the prosperity of large language models (LLMs), powerful LLM-based intelligent agents have been developed to provide customized services with a set of user-defined tools. State-of-the-art methods for constructing LLM agents adopt…

Computation and Language · Computer Science 2024-06-06 Yifei Wang , Dizhan Xue , Shengjie Zhang , Shengsheng Qian

Large language models (LLMs) are widely deployed across various applications, often with safeguards to prevent the generation of harmful or restricted content. However, these safeguards can be covertly bypassed through adversarial…

Cryptography and Security · Computer Science 2025-11-04 Kasimir Schulz , Amelia Kawasaki , Leo Ring

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…

Cryptography and Security · Computer Science 2023-12-11 Shuli Jiang , Swanand Ravindra Kadhe , Yi Zhou , Ling Cai , Nathalie Baracaldo