English
Related papers

Related papers: CodePurify: Defend Backdoor Attacks on Neural Code…

200 papers

Recent studies have demonstrated the susceptibility of deep neural networks to backdoor attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be dominated by the trigger information, though trigger…

Artificial Intelligence · Computer Science 2023-06-30 Mingli Zhu , Shaokui Wei , Hongyuan Zha , Baoyuan Wu

Deep neural networks demonstrate impressive performance in visual recognition, but they remain vulnerable to adversarial attacks that is imperceptible to the human. Although existing defense strategies such as adversarial training and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Zhe Li , Bernhard Kainz

Neural networks are susceptible to data inference attacks such as the model inversion attack and the membership inference attack, where the attacker could infer the reconstruction and the membership of a data sample from the confidence…

Cryptography and Security · Computer Science 2020-08-21 Ziqi Yang , Bin Shao , Bohan Xuan , Ee-Chien Chang , Fan Zhang

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 Neural Networks (DNNs) are known to be vulnerable to both backdoor and adversarial attacks. In the literature, these two types of attacks are commonly treated as distinct robustness problems and solved separately, since they belong to…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Zhenxing Niu , Yuyao Sun , Qiguang Miao , Rong Jin , Gang Hua

Adversarial attacks can mislead neural network classifiers. The defense against adversarial attacks is important for AI safety. Adversarial purification is a family of approaches that defend adversarial attacks with suitable pre-processing.…

Machine Learning · Computer Science 2023-10-31 Boya Zhang , Weijian Luo , Zhihua Zhang

Code Language Models (CLMs), particularly those leveraging deep learning, have achieved significant success in code intelligence domain. However, the issue of security, particularly backdoor attacks, is often overlooked in this process. The…

Cryptography and Security · Computer Science 2025-05-20 Guang Yang , Yu Zhou , Xiang Chen , Xiangyu Zhang , Terry Yue Zhuo , David Lo , Taolue Chen

Deep neural networks are vulnerable to a range of adversaries. A particularly pernicious class of vulnerabilities are backdoors, where model predictions diverge in the presence of subtle triggers in inputs. An attacker can implant a…

Machine Learning · Computer Science 2022-12-20 Goutham Ramakrishnan , Aws Albarghouthi

Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and…

Cryptography and Security · Computer Science 2024-06-12 Shenao Yan , Shen Wang , Yue Duan , Hanbin Hong , Kiho Lee , Doowon Kim , Yuan Hong

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

Deep neural networks have achieved impressive performance in a variety of tasks over the last decade, such as autonomous driving, face recognition, and medical diagnosis. However, prior works show that deep neural networks are easily…

Cryptography and Security · Computer Science 2022-10-24 Jiyang Guan , Zhuozhuo Tu , Ran He , Dacheng Tao

Machine learning (ML) has gained significant adoption in Android malware detection to address the escalating threats posed by the rapid proliferation of malware attacks. However, recent studies have revealed the inherent vulnerabilities of…

Cryptography and Security · Computer Science 2026-05-07 Yuyang Zhou , Guang Cheng , Zongyao Chen , Shui Yu

Adversarial purification is a kind of defense technique that can defend against various unseen adversarial attacks without modifying the victim classifier. Existing methods often depend on external generative models or cooperation between…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Erhu Liu , Zonglin Yang , Bo Liu , Bin Xiao , Xiuli Bi

The widespread adoption of code language models in software engineering tasks has exposed vulnerabilities to adversarial attacks, especially the identifier substitution attacks. Although existing identifier substitution attackers…

Software Engineering · Computer Science 2025-04-29 Wenhan Mu , Ling Xu , Shuren Pei , Le Mi , Huichi Zhou

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a large-scale Pre-trained Language Model (PLM) with poisoned…

Computation and Language · Computer Science 2022-10-19 Zhiyuan Zhang , Lingjuan Lyu , Xingjun Ma , Chenguang Wang , Xu Sun

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Machine Learning · Computer Science 2025-09-29 Sujeevan Aseervatham , Achraf Kerzazi , Younès Bennani

Model pruning has gained traction as a promising defense strategy against backdoor attacks in deep learning. However, existing pruning-based approaches often fall short in accurately identifying and removing the specific parameters…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly…

Machine Learning · Computer Science 2025-04-08 Min Liu , Alberto Sangiovanni-Vincentelli , Xiangyu Yue

Adversarial attacks meticulously generate minuscule, imperceptible perturbations to images to deceive neural networks. Counteracting these, adversarial purification methods seek to transform adversarial input samples into clean output…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Sitong Liu , Zhichao Lian , Shuangquan Zhang , Liang Xiao

The recently proposed facial cloaking attacks add invisible perturbation (cloaks) to facial images to protect users from being recognized by unauthorized facial recognition models. However, we show that the "cloaks" are not robust enough…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Jing Wen