English
Related papers

Related papers: Defensive Distillation is Not Robust to Adversaria…

200 papers

Defending against adversarial examples remains an open problem. A common belief is that randomness at inference increases the cost of finding adversarial inputs. An example of such a defense is to apply a random transformation to inputs…

Machine Learning · Computer Science 2022-10-13 Yue Gao , Ilia Shumailov , Kassem Fawaz , Nicolas Papernot

Frontier models that generate extended reasoning traces inadvertently produce rich token sequences that can facilitate model distillation. Recognizing this vulnerability, model owners may seek sampling strategies that limit the…

Artificial Intelligence · Computer Science 2025-10-28 Yash Savani , Asher Trockman , Zhili Feng , Yixuan Even Xu , Avi Schwarzschild , Alexander Robey , Marc Finzi , J. Zico Kolter

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such…

Machine Learning · Statistics 2019-11-19 Sanjay Kariyappa , Moinuddin K Qureshi

In recent years, the rapid development of deep neural networks has brought increased attention to the security and robustness of these models. While existing adversarial attack algorithms have demonstrated success in improving adversarial…

Machine Learning · Computer Science 2025-02-25 Wenyuan Wu , Zheng Liu , Yong Chen , Chao Su , Dezhong Peng , Xu Wang

Deep learning models are vulnerable to backdoor attacks, where attackers inject malicious behavior through data poisoning and later exploit triggers to manipulate deployed models. To improve the stealth and effectiveness of backdoors, prior…

Cryptography and Security · Computer Science 2024-09-10 Xiaolei Liu , Ming Yi , Kangyi Ding , Bangzhou Xin , Yixiao Xu , Li Yan , Chao Shen

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples which contain human-imperceptible perturbations. A series of defending methods, either proactive defence or reactive defence, have been proposed in the recent…

Machine Learning · Computer Science 2020-07-27 Derek Wang , Chaoran Li , Sheng Wen , Surya Nepal , Yang Xiang

Deep neural networks are learning models having achieved state of the art performance in many fields like prediction, computer vision, language processing and so on. However, it has been shown that certain inputs exist which would not trick…

Machine Learning · Computer Science 2020-06-03 Jay N. Paranjape , Rahul Kumar Dubey , Vijendran V Gopalan

Distillation via sampling reasoning traces exposes closed-source frontier models to adversarial third parties who can bypass their guardrails and misappropriate their capabilities. Antidistillation methods aim to address this by poisoning…

Cryptography and Security · Computer Science 2026-05-12 Max Hartman , Vidhata Jayaraman , Moulik Choraria , Yash Savani , Lav R. Varshney

The design of a security scheme for beamforming prediction is critical for next-generation wireless networks (5G, 6G, and beyond). However, there is no consensus about protecting the beamforming prediction using deep learning algorithms in…

Cryptography and Security · Computer Science 2022-02-17 Murat Kuzlu , Ferhat Ozgur Catak , Umit Cali , Evren Catak , Ozgur Guler

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and…

Machine Learning · Computer Science 2020-11-03 Aditi Raghunathan , Jacob Steinhardt , Percy Liang

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…

Machine Learning · Computer Science 2019-07-08 Yuzhe Ma , Xiaojin Zhu , Justin Hsu

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify…

Machine Learning · Computer Science 2021-05-26 Leo Schwinn , René Raab , An Nguyen , Dario Zanca , Bjoern Eskofier

Deep learning is vulnerable to adversarial examples. Many defenses based on randomized neural networks have been proposed to solve the problem, but fail to achieve robustness against attacks using proxy gradients such as the Expectation…

Machine Learning · Computer Science 2021-07-07 Sungyoon Lee , Hoki Kim , Jaewook Lee

Data-driven deep learning (DL) techniques developed for automatic modulation classification (AMC) of wireless signals are vulnerable to adversarial attacks. This poses a severe security threat to the DL-based wireless systems, specifically…

Signal Processing · Electrical Eng. & Systems 2024-04-25 Nayan Moni Baishya , B. R. Manoj

Machine learning systems based on deep neural networks (DNNs) have gained mainstream adoption in many applications. Recently, however, DNNs are shown to be vulnerable to adversarial example attacks with slight perturbations on the inputs.…

Machine Learning · Computer Science 2018-12-10 Bo Luo , Min Li , Yu Li , Qiang Xu

Transfer learning is prevalent as a technique to efficiently generate new models (Student models) based on the knowledge transferred from a pre-trained model (Teacher model). However, Teacher models are often publicly available for sharing…

Machine Learning · Computer Science 2022-02-10 Bang Wu , Shuo Wang , Xingliang Yuan , Cong Wang , Carsten Rudolph , Xiangwen Yang

In ordinary distillation, student networks are trained with soft labels (SLs) given by pretrained teacher networks, and students are expected to improve upon teachers since SLs are stronger supervision than the original hard labels.…

Machine Learning · Computer Science 2022-03-11 Jianing Zhu , Jiangchao Yao , Bo Han , Jingfeng Zhang , Tongliang Liu , Gang Niu , Jingren Zhou , Jianliang Xu , Hongxia Yang

The inadvertent stealing of private/sensitive information using Knowledge Distillation (KD) has been getting significant attention recently and has guided subsequent defense efforts considering its critical nature. Recent work Nasty Teacher…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Surgan Jandial , Yash Khasbage , Arghya Pal , Vineeth N Balasubramanian , Balaji Krishnamurthy

In recent years, deep learning has shown impressive performance on many tasks. However, recent researches showed that deep learning systems are vulnerable to small, specially crafted perturbations that are imperceptible to humans. Images…

Computer Vision and Pattern Recognition · Computer Science 2020-01-01 Hao Ge , Xiaoguang Tu , Mei Xie , Zheng Ma

Convolutional neural networks (CNNs) excel in computer vision but are susceptible to adversarial attacks, crafted perturbations designed to mislead predictions. Despite advances in adversarial training, a gap persists between model accuracy…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Hayat Ullah , Syed Muhammad Talha Zaidi , Arslan Munir