English
Related papers

Related papers: Architectural Neural Backdoors from First Principl…

200 papers

This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is based on the intuition that the feature extraction layers of…

Machine Learning · Computer Science 2023-02-24 Hao Fu , Akshaj Kumar Veldanda , Prashanth Krishnamurthy , Siddharth Garg , Farshad Khorrami

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

Computer Vision and Pattern Recognition · Computer Science 2019-12-24 Aniruddha Saha , Akshayvarun Subramanya , Hamed Pirsiavash

Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing…

Cryptography and Security · Computer Science 2020-09-01 Shaofeng Li , Minhui Xue , Benjamin Zi Hao Zhao , Haojin Zhu , Xinpeng Zhang

Backdoor attacks pose significant security risks for Large Language Models (LLMs), yet the internal mechanisms by which triggers operate remain poorly understood. We present the first mechanistic analysis of language-switching backdoors,…

Computation and Language · Computer Science 2026-02-16 Théo Lasnier , Wissam Antoun , Francis Kulumba , Djamé Seddah

Neural networks have achieved state-of-the-art performance in solving many problems, including many applications in safety/security-critical systems. Researchers also discovered multiple security issues associated with neural networks. One…

Cryptography and Security · Computer Science 2022-05-17 Long H. Pham , Jun Sun

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…

Computation and Language · Computer Science 2022-11-23 Xuan Sheng , Zhaoyang Han , Piji Li , Xiangmao Chang

Backdoor attacks pose a significant threat to the security and reliability of deep learning models. To mitigate such attacks, one promising approach is to learn to extract features from the target model and use these features for backdoor…

Machine Learning · Computer Science 2025-12-24 Zhonghao Yang , Cheng Luo , Daojing He , Yiming Li , Yu Li

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Computation and Language · Computer Science 2021-11-02 Lujia Shen , Shouling Ji , Xuhong Zhang , Jinfeng Li , Jing Chen , Jie Shi , Chengfang Fang , Jianwei Yin , Ting Wang

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of the infected model will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger, while it…

Cryptography and Security · Computer Science 2021-02-02 Yiming Li , Tongqing Zhai , Baoyuan Wu , Yong Jiang , Zhifeng Li , Shutao Xia

The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…

Cryptography and Security · Computer Science 2023-10-19 Ganghua Wang , Xun Xian , Jayanth Srinivasa , Ashish Kundu , Xuan Bi , Mingyi Hong , Jie Ding

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yangming Chen

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works require high computational overhead or backdoor attack…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Mingfu Xue , Yinghao Wu , Zhiyu Wu , Yushu Zhang , Jian Wang , Weiqiang Liu

Machine learning (ML) has made tremendous progress during the past decade and is being adopted in various critical real-world applications. However, recent research has shown that ML models are vulnerable to multiple security and privacy…

Cryptography and Security · Computer Science 2022-03-07 Ahmed Salem , Rui Wen , Michael Backes , Shiqing Ma , Yang Zhang

Backdoor attack against deep neural networks is currently being profoundly investigated due to its severe security consequences. Current state-of-the-art backdoor attacks require the adversary to modify the input, usually by adding a…

Cryptography and Security · Computer Science 2020-10-09 Ahmed Salem , Michael Backes , Yang Zhang

Deep neural networks face persistent challenges in defending against backdoor attacks, leading to an ongoing battle between attacks and defenses. While existing backdoor defense strategies have shown promising performance on reducing attack…

Computer Vision and Pattern Recognition · Computer Science 2024-05-31 Mingli Zhu , Siyuan Liang , Baoyuan Wu

Backdoor attacks are rapidly emerging threats to deep neural networks (DNNs). In the backdoor attack scenario, attackers usually implant the backdoor into the target model by manipulating the training dataset or training process. Then, the…

Cryptography and Security · Computer Science 2022-05-09 Nan Zhong , Zhenxing Qian , Xinpeng Zhang

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Chengxiao Luo , Yiming Li , Yong Jiang , Shu-Tao Xia

Code LLMs are increasingly employed in software development. However, studies have shown that they are vulnerable to backdoor attacks: when a trigger (a specific input pattern) appears in the input, the backdoor will be activated and cause…

Cryptography and Security · Computer Science 2025-10-07 Chenyu Wang , Zhou Yang , Yaniv Harel , David Lo

Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic…

Cryptography and Security · Computer Science 2026-04-15 Haotian Jin , Yang Li , Haihui Fan , Lin Shen , Xiangfang Li , Bo Li

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Computation and Language · Computer Science 2026-02-02 Anindya Sundar Das , Kangjie Chen , Monowar Bhuyan