English
Related papers

Related papers: Neural Trojans

200 papers

While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM input space is discrete, which precludes gradient-based…

Machine Learning · Computer Science 2025-09-22 Zhengxing Li , Guangmingmei Yang , Jayaram Raghuram , David J. Miller , George Kesidis

In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a…

Cryptography and Security · Computer Science 2021-09-06 Guanxiong Liu , Issa Khalil , Abdallah Khreishah , NhatHai Phan

Neural networks are successfully used in a variety of applications, many of them having safety and security concerns. As a result researchers have proposed formal verification techniques for verifying neural network properties. While…

Cryptography and Security · Computer Science 2022-05-10 Youcheng Sun , Muhammad Usman , Divya Gopinath , Corina S. Păsăreanu

Deep neural networks have achieved state-of-the-art performance on various tasks. However, lack of interpretability and transparency makes it easier for malicious attackers to inject trojan backdoor into the neural networks, which will make…

Cryptography and Security · Computer Science 2019-11-19 Xijie Huang , Moustafa Alzantot , Mani Srivastava

As spiking neural networks (SNNs) are deployed increasingly in real-world efficiency critical applications, the security concerns in SNNs attract more attention. Currently, researchers have already demonstrated an SNN can be attacked with…

Neural and Evolutionary Computing · Computer Science 2022-05-04 Ling Liang , Kaidi Xu , Xing Hu , Lei Deng , Yuan Xie

Cybersecurity attacks are growing both in frequency and sophistication over the years. This increasing sophistication and complexity call for more advancement and continuous innovation in defensive strategies. Traditional methods of…

Machine Learning · Computer Science 2020-01-20 Antoine Delplace , Sheryl Hermoso , Kristofer Anandita

Malware continues to be a major cyber threat, despite the tremendous effort that has been made to combat them. The number of malware in the wild steadily increases over time, meaning that we must resort to automated defense techniques. This…

Cryptography and Security · Computer Science 2020-09-17 Deqiang Li , Qianmu Li , Yanfang Ye , Shouhuai Xu

Machine learning and deep learning in particular has advanced tremendously on perceptual tasks in recent years. However, it remains vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the…

Machine Learning · Statistics 2017-02-22 Jan Hendrik Metzen , Tim Genewein , Volker Fischer , Bastian Bischoff

As spiking neural networks (SNNs) gain traction in deploying neuromorphic computing solutions, protecting their intellectual property (IP) has become crucial. Without adequate safeguards, proprietary SNN architectures are at risk of theft,…

Cryptography and Security · Computer Science 2025-01-31 Hamed Poursiami , Ihsen Alouani , Maryam Parsa

In recent years, neural networks have become the default choice for image classification and many other learning tasks, even though they are vulnerable to so-called adversarial attacks. To increase their robustness against these attacks,…

Machine Learning · Computer Science 2020-02-10 Hasan Ferit Eniser , Maria Christakis , Valentin Wüstholz

Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions…

Machine Learning · Computer Science 2017-11-28 Andrew Slavin Ross , Finale Doshi-Velez

The success of deep neural networks (DNNs) in real-world applications has benefited from abundant pre-trained models. However, the backdoored pre-trained models can pose a significant trojan threat to the deployment of downstream DNNs.…

Cryptography and Security · Computer Science 2024-07-18 Haibo Jin , Ruoxi Chen , Jinyin Chen , Haibin Zheng , Yang Zhang , Haohan Wang

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

Cryptography and Security · Computer Science 2025-01-08 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

Along with the success of deep neural network (DNN) models, rise the threats to the integrity of these models. A recent threat is the Trojan attack where an attacker interferes with the training pipeline by inserting triggers into some of…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Marzieh Edraki , Nazmul Karim , Nazanin Rahnavard , Ajmal Mian , Mubarak Shah

The increasing cost of integrated circuit (IC) fabrication has driven most companies to "go fabless" over time. The corresponding outsourcing trend gave rise to various attack vectors, e.g., illegal overproduction of ICs, piracy of the…

Cryptography and Security · Computer Science 2019-02-26 Johann Knechtel , Satwik Patnaik , Ozgur Sinanoglu

Despite their advances and success, real-world deep neural networks are known to be vulnerable to adversarial attacks. Universal adversarial perturbation, an input-agnostic attack, poses a serious threat for them to be deployed in…

Machine Learning · Computer Science 2025-02-11 Bing Sun , Jun Sun , Wei Zhao

Neural networks perform exceedingly well across various machine learning tasks but are not immune to adversarial perturbations. This vulnerability has implications for real-world applications. While much research has been conducted, the…

Machine Learning · Computer Science 2023-10-02 Dennis Y. Menn , Tzu-hsun Feng , Sriram Vishwanath , Hung-yi Lee

Recent research shows deep neural networks are vulnerable to different types of attacks, such as adversarial attack, data poisoning attack and backdoor attack. Among them, backdoor attack is the most cunning one and can occur in almost…

Cryptography and Security · Computer Science 2022-09-14 Jie Zhang , Dongdong Chen , Qidong Huang , Jing Liao , Weiming Zhang , Huamin Feng , Gang Hua , Nenghai Yu

Deep Neural Networks (DNNs) have become a powerful toolfor a wide range of problems. Yet recent work has found an increasing variety of adversarial samplesthat can fool them. Most existing detection mechanisms against adversarial…

Machine Learning · Computer Science 2019-11-22 Ilia Shumailov , Yiren Zhao , Robert Mullins , Ross Anderson

Deep neural networks are vulnerable to attacks from adversarial inputs and, more recently, Trojans to misguide or hijack the model's decision. We expose the existence of an intriguing class of spatially bounded, physically realizable,…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Bao Gia Doan , Minhui Xue , Shiqing Ma , Ehsan Abbasnejad , Damith C. Ranasinghe