English
Related papers

Related papers: Defending Against Backdoor Attacks in Natural Lang…

200 papers

Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…

Computation and Language · Computer Science 2024-10-08 Yongjie Wang , Xiaoqi Qiu , Yu Yue , Xu Guo , Zhiwei Zeng , Yuhong Feng , Zhiqi Shen

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

Backdoor attacks pose a significant security threat to natural language processing (NLP) systems, but existing methods lack explainable trigger mechanisms and fail to quantitatively model vulnerability patterns. This work pioneers the…

Cryptography and Security · Computer Science 2025-09-24 Gejian Zhao , Hanzhou Wu , Xinpeng Zhang

Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditional data poisoning or parameter manipulation, architectural…

Cryptography and Security · Computer Science 2025-07-18 Victoria Childress , Josh Collyer , Jodie Knapp

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…

Machine Learning · Statistics 2019-12-10 Alexander Turner , Dimitris Tsipras , Aleksander Madry

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…

Cryptography and Security · Computer Science 2023-05-01 Jiazhao Li , Yijin Yang , Zhuofeng Wu , V. G. Vinod Vydiswaran , Chaowei Xiao

Backdoor attacks have become a critical threat to deep neural networks (DNNs), drawing many research interests. However, most of the studied attacks employ a single type of trigger. Consequently, proposed backdoor defenders often rely on…

Cryptography and Security · Computer Science 2025-01-14 Duc Anh Vu , Anh Tuan Tran , Cong Tran , Cuong Pham

With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual…

Computation and Language · Computer Science 2024-04-03 Ying Zhou , Ben He , Le Sun

Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics. Most methods use the gradient to attack the model on each sample independently. Instead of…

Computation and Language · Computer Science 2021-09-02 Badr Youbi Idrissi , Stéphane Clinchant

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Cryptography and Security · Computer Science 2021-06-18 Giovanni Apruzzese , Mauro Andreolini , Luca Ferretti , Mirco Marchetti , Michele Colajanni

Natural language understanding (NLU) and natural language generation (NLG) are two fundamental and related tasks in building task-oriented dialogue systems with opposite objectives: NLU tackles the transformation from natural language to…

Computation and Language · Computer Science 2020-06-16 Bo-Hsiang Tseng , Jianpeng Cheng , Yimai Fang , David Vandyke

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks. However, they remain vulnerable to backdoor attacks, where models behave normally for…

Computation and Language · Computer Science 2025-08-29 Chen Chen , Yuchen Sun , Jiaxin Gao , Xueluan Gong , Qian Wang , Ziyao Wang , Yongsen Zheng , Kwok-Yan Lam

As large language models (LLMs) continue to evolve, it is critical to assess the security threats and vulnerabilities that may arise both during their training phase and after models have been deployed. This survey seeks to define and…

Cryptography and Security · Computer Science 2025-05-05 Francisco Aguilera-Martínez , Fernando Berzal

Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…

Cryptography and Security · Computer Science 2025-08-07 Xiaohu Li , Yunfeng Ning , Zepeng Bao , Mayi Xu , Jianhao Chen , Tieyun Qian

Natural Language Generation (NLG) has made great progress in recent years due to the development of deep learning techniques such as pre-trained language models. This advancement has resulted in more fluent, coherent and even properties…

Computation and Language · Computer Science 2022-03-11 Wei Li , Wenhao Wu , Moye Chen , Jiachen Liu , Xinyan Xiao , Hua Wu

Recent language models, especially those based on recurrent neural networks (RNNs), make it possible to generate natural language from a learned probability. Language generation has wide applications including machine translation,…

Computation and Language · Computer Science 2016-01-05 Lili Mou , Rui Yan , Ge Li , Lu Zhang , Zhi Jin

It has been proved that deep neural networks are facing a new threat called backdoor attacks, where the adversary can inject backdoors into the neural network model through poisoning the training dataset. When the input containing some…

Cryptography and Security · Computer Science 2021-03-16 Chuanshuai Chen , Jiazhu Dai

Generative language models are increasingly used for contract drafting and enhancement, creating a scenario where competing parties deploy different language models against each other. This introduces not only a game-theory challenge but…

Computation and Language · Computer Science 2025-01-03 Arinbjörn Kolbeinsson , Benedikt Kolbeinsson

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

Cryptography and Security · Computer Science 2026-03-17 Jianwei Li , Jung-Eun Kim

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Machine Learning · Computer Science 2022-11-02 Ganqu Cui , Lifan Yuan , Bingxiang He , Yangyi Chen , Zhiyuan Liu , Maosong Sun