English
Related papers

Related papers: Inverting Trojans in LLMs

200 papers

Backdoor (Trojan) attacks are an important type of adversarial exploit against deep neural networks (DNNs), wherein a test instance is (mis)classified to the attacker's target class whenever the attacker's backdoor trigger is present. In…

Machine Learning · Computer Science 2023-08-22 Xi Li , Zhen Xiang , David J. Miller , George Kesidis

Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Juncheng Li , Yige Li , Hanxun Huang , Yunhao Chen , Xin Wang , Yixu Wang , Xingjun Ma , Yu-Gang Jiang

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, existing defense strategies suffer from limited…

Cryptography and Security · Computer Science 2025-10-13 Shuai Zhao , Xinyi Wu , Shiqian Zhao , Xiaobao Wu , Zhongliang Guo , Yanhao Jia , Anh Tuan Luu

Many large language models (LLMs) use reasoning to generate responses but do not reveal their full reasoning traces (a.k.a. chains of thought), instead outputting only final answers and brief reasoning summaries. To demonstrate that hiding…

Cryptography and Security · Computer Science 2026-05-14 Tingwei Zhang , John X. Morris , Vitaly Shmatikov

Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. However, recent works show that LLMs' intrinsic self-correction fails without oracle labels as feedback…

Computation and Language · Computer Science 2025-07-16 Qingjie Zhang , Di Wang , Haoting Qian , Yiming Li , Tianwei Zhang , Minlie Huang , Ke Xu , Hewu Li , Yan Liu , Han Qiu

Due to the high cost of training, large model (LM) practitioners commonly use pretrained models downloaded from untrusted sources, which could lead to owning compromised models. In-context learning is the ability of LMs to perform multiple…

Cryptography and Security · Computer Science 2024-09-09 Gorka Abad , Stjepan Picek , Lorenzo Cavallaro , Aitor Urbieta

Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attacks generally operate by fixing an adversarial instruction…

Machine Learning · Computer Science 2026-05-07 Marco Rando , Samuel Vaiter

Grounding large language models (LLMs) in external knowledge sources is a promising method for faithful prediction. While existing grounding approaches work well for simple queries, many real-world information needs require synthesizing…

Computation and Language · Computer Science 2025-09-23 Cheng Jiayang , Qianqian Zhuang , Haoran Li , Chunkit Chan , Xin Liu , Lin Qiu , Yangqiu Song

Dense retrieval systems have been widely used in various NLP applications. However, their vulnerabilities to potential attacks have been underexplored. This paper investigates a novel attack scenario where the attackers aim to mislead the…

Computation and Language · Computer Science 2025-08-26 Quanyu Long , Yue Deng , LeiLei Gan , Wenya Wang , Sinno Jialin Pan

Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the context of LLMs deployed as Web Services, which typically…

Computation and Language · Computer Science 2025-02-13 Wenjie Mo , Jiashu Xu , Qin Liu , Jiongxiao Wang , Jun Yan , Hadi Askari , Chaowei Xiao , Muhao Chen

Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversarial perturbations. In contrast to common inference-time…

Computer Vision and Pattern Recognition · Computer Science 2020-05-14 Ali Borji

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

Computation and Language · Computer Science 2021-01-18 Lichao Sun

Backdoor attacks creating 'sleeper agents' in large language models (LLMs) pose significant safety risks. This study employs mechanistic interpretability to explore resulting internal structural differences. Comparing clean Qwen2.5-3B…

Computation and Language · Computer Science 2025-08-25 Mohammed Abu Baker , Lakshmi Babu-Saheer

Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw…

Cryptography and Security · Computer Science 2025-12-09 Tianhang Zhao , Wei Du , Haodong Zhao , Sufeng Duan , Gongshen Liu

Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…

Machine Learning · Computer Science 2025-06-03 Toan Tran , Ruixuan Liu , Li Xiong

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…

Cryptography and Security · Computer Science 2024-04-02 Hai Huang , Zhengyu Zhao , Michael Backes , Yun Shen , Yang Zhang

Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and…

Cryptography and Security · Computer Science 2024-10-30 Wenkai Yang , Xiaohan Bi , Yankai Lin , Sishuo Chen , Jie Zhou , Xu Sun

Backdoor attacks are a significant threat to the performance and integrity of pre-trained language models. Although such models are routinely fine-tuned for downstream NLP tasks, recent work shows they remain vulnerable to backdoor attacks…

Machine Learning · Computer Science 2025-08-28 Santosh Chapagain , Shah Muhammad Hamdi , Soukaina Filali Boubrahimi

This paper investigates the challenging task of detecting backdoored text-to-image models under black-box settings and introduces a novel detection framework BlackMirror. Existing approaches typically rely on analyzing image-level…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Feiran Li , Qianqian Xu , Shilong Bao , Zhiyong Yang , Xilin Zhao , Xiaochun Cao , Qingming Huang
‹ Prev 1 3 4 5 6 7 10 Next ›