English
Related papers

Related papers: Inverting Trojans in LLMs

200 papers

This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the model's token predictions derived from intermediate…

Computation and Language · Computer Science 2025-06-10 Jaturong Kongmanee

Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus…

Cryptography and Security · Computer Science 2025-10-01 Miao Yu , Zhenhong Zhou , Moayad Aloqaily , Kun Wang , Biwei Huang , Stephen Wang , Yueming Jin , Qingsong Wen

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…

Large language models (LLMs) are becoming an integrated part of software development. These models are trained on large datasets for code, where it is hard to verify each data point. Therefore, a potential attack surface can be to inject…

Software Engineering · Computer Science 2023-12-12 Aftab Hussain , Md Rafiqul Islam Rabin , Toufique Ahmed , Mohammad Amin Alipour , Bowen Xu

Backdoor (Trojan) attacks are emerging threats against deep neural networks (DNN). A DNN being attacked will predict to an attacker-desired target class whenever a test sample from any source class is embedded with a backdoor pattern; while…

Cryptography and Security · Computer Science 2021-12-08 Xi Li , Zhen Xiang , David J. Miller , George Kesidis

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Computation and Language · Computer Science 2026-04-21 Dang Huu-Tien , Hoang Thanh-Tung , Anh Bui , Minh-Phuong Nguyen , Le-Minh Nguyen , Naoya Inoue

Stealthy data poisoning during fine-tuning can backdoor large language models (LLMs), threatening downstream safety. Existing detectors either use classifier-style probability signals--ill-suited to generation--or rely on rewriting, which…

Computation and Language · Computer Science 2025-11-13 Jinwen Chen , Hainan Zhang , Fei Sun , Qinnan Zhang , Sijia Wen , Ziwei Wang , Zhiming Zheng

Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this…

Computation and Language · Computer Science 2026-03-31 Duanyi Yao , Changyue Li , Zhicong Huang , Cheng Hong , Songze Li

Talent recruitment is a critical, yet costly process for many industries, with high recruitment costs and long hiring cycles. Existing talent recommendation systems increasingly adopt large language models (LLMs) due to their remarkable…

Computation and Language · Computer Science 2026-04-03 Silin Du , Hongyan Liu

At present, backdoor attacks attract attention as they do great harm to deep learning models. The adversary poisons the training data making the model being injected with a backdoor after being trained unconsciously by victims using the…

Cryptography and Security · Computer Science 2023-03-06 Shengfang Zhai , Qingni Shen , Xiaoyi Chen , Weilong Wang , Cong Li , Yuejian Fang , Zhonghai Wu

Prompt-tuning has emerged as an attractive paradigm for deploying large-scale language models due to its strong downstream task performance and efficient multitask serving ability. Despite its wide adoption, we empirically show that…

Computation and Language · Computer Science 2023-10-17 Chengkun Wei , Wenlong Meng , Zhikun Zhang , Min Chen , Minghu Zhao , Wenjing Fang , Lei Wang , Zihui Zhang , Wenzhi Chen

Estimating uncertainty in Large Language Models (LLMs) is important for properly evaluating LLMs, and ensuring safety for users. However, prior approaches to uncertainty estimation focus on the final answer in generated text, ignoring…

Computation and Language · Computer Science 2024-12-12 Eric Bigelow , Ari Holtzman , Hidenori Tanaka , Tomer Ullman

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Cryptography and Security · Computer Science 2025-01-08 Peihai Jiang , Xixiang Lyu , Yige Li , Jing Ma

Deep speech classification has achieved tremendous success and greatly promoted the emergence of many real-world applications. However, backdoor attacks present a new security threat to it, particularly with untrustworthy third-party…

Sound · Computer Science 2023-08-15 Zhe Ye , Terui Mao , Li Dong , Diqun Yan

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

Large Language Models (LLMs) have the promise to revolutionize computing broadly, but their complexity and extensive training data also expose significant privacy vulnerabilities. One of the simplest privacy risks associated with LLMs is…

Machine Learning · Computer Science 2024-09-25 Rongting Zhang , Martin Bertran , Aaron Roth

Neural networks can conceal malicious Trojan backdoors that allow a trigger to covertly change the model behavior. Detecting signs of these backdoors, particularly without access to any triggered data, is the subject of ongoing research and…

Machine Learning · Computer Science 2024-11-07 Todd Huster , Peter Lin , Razvan Stefanescu , Emmanuel Ekwedike , Ritu Chadha

With the widespread adoption of Large Language Models (LLMs) and increasingly stringent privacy regulations, protecting data privacy in LLMs has become essential, especially for privacy-sensitive applications. Membership Inference Attacks…

Cryptography and Security · Computer Science 2026-01-30 Md Tasnim Jawad , Mingyan Xiao , Yanzhao Wu

The rapid advancement of large language models (LLMs) has sparked growing interest in understanding their security vulnerabilities, particularly Trojan attacks that enable stealthy manipulation of model behavior. Traditional Trojan methods…

Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this ability also heightens the risk of identity impersonation. To the best of our knowledge, no…

Computation and Language · Computer Science 2026-05-01 Lang Gao , Xuhui Li , Chenxi Wang , Mingzhe Li , Wei Liu , Zirui Song , Jinghui Zhang , Rui Yan , Preslav Nakov , Xiuying Chen