21 papers · ranked by Valyu relevance
Kaleel Mahmood, Deniz Gurevin, Marten van Dijk, Phuoung Ha Nguyen + 1 more
'Luis Hernández-Callejo'] Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR. These defenses are mainly focused on mitigating white-box attacks. They do not properly examine black-box attacks. In this paper, we expand upon the analyses of these defenses to include adaptive black-box…
Han Cao, Chengxiang Si, Qindong Sun, Yanxiao Liu + 3 more
'Prosanta Gope' 'Gholamreza Anbarjafari'] The vulnerability of deep neural network (DNN)-based systems makes them susceptible to adversarial perturbation and may cause classification task failure. In this work, we propose an adversarial attack model using the Artificial Bee Colony (ABC) algorithm to generate…
Naveed Akhtar, Ajmal Mian, Navid Kardan, Mubarak Shah
—Deep Learning (DL) is the most widely used tool in the contemporary field of computer vision. Its ability to accurately solve complex problems is employed in vision research to learn deep neural models for a variety of tasks, including security critical applications. However, it is now known that DL is vulnerable to…
Naveed Akhtar, Ajmal Mian
ACKNOWLEDGEMENTS: The authors thank Nicholas Carlini (UC Berkeley) and Dimitris Tsipras (MIT) for feedback to improve the survey quality. We also acknowledge X. Huang (Uni. Liverpool), K. R. Reddy (IISC), E. Valle (UNICAMP), Y. Yoo (CLAIR) and others for providing pointers to make the survey more comprehensive. This…
Gaoming Yang, Mingwei Li, Xianjing Fang, Ji Zhang + 2 more
'Yilun Shang'] Adversarial examples are regarded as a security threat to deep learning models, and there are many ways to generate them. However, most existing methods require the query authority of the target during their work. In a more practical situation, the attacker will be easily detected because of too many…
Yongsu Kim, Hyoeun Kang, Naufal Suryanto, Harashta Tatimma Larasati + 3 more
'Afifatul Mukaroh' 'Howon Kim' 'Ilsun You'] Deep neural networks (DNNs), especially those used in computer vision, are highly vulnerable to adversarial attacks, such as adversarial perturbations and adversarial patches. Adversarial patches, often considered more appropriate for a real-world attack, are attached to the…
Shashank Kotyan
—Deep Learning has empowered us to train neural networks for complex data with high performance. However, with the growing research, several vulnerabilities in neural networks have been exposed. A particular branch of research, Adversarial Machine Learning, exploits and understands some of the vulnerabilities that…
Gabriel Resende Machado, Eugênio Silva, Ronaldo Ribeiro Goldschmidt
Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving cars. However, recent works have shown those algorithms, which can even surpass the human capabilities, are…
Xu Han, Yao Ma, Haochen Liu, Debayan Deb + 3 more
'Anil K. Jain'] Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in…
Jin-Tao Yang, Hao Jiang, Hao Li, Dong-Sheng Ye + 4 more
'Andrea Prati' 'Luis Javier García Villalba' 'Vincent A. Cicirello'] Adversarial examples present a severe threat to deep neural networks’ application in safetycritical domains such as autonomous driving. Although there are numerous defensive solutions, they all have some flaws, such as the fact that they can only…
Olga Taran, Shideh Rezaeifar, Taras Holotyak, Slava Voloshynovskiy
In recent years, classification techniques based on deep neural networks (DNN) were widely used in many fields such as computer vision, natural language processing, and self-driving cars. However, the vulnerability of the DNN-based classification systems to adversarial attacks questions their usage in many critical…
Narmin Ghaffari Laleh, Daniel Truhn, Gregory Patrick Veldhuizen, Tianyu Han + 7 more
Artificial Intelligence (AI) can support diagnostic workflows in oncology by aiding diagnosis and providing biomarkers. AI applications are therefore expected to evolve from academic prototypes to commercial products in the coming years. However, AI applications are vulnerable to adversarial attacks, such as malicious…
Daniel Mas Montserrat, Alexander G. Ioannidis
Adversarial attacks can drastically change the output of a method by performing a small change on its input. While they can be a useful framework to analyze worst-case robustness, they can also be used by malicious agents to perform damage in machine learning-based applications. The proliferation of platforms that…
Jenelle Feather, Guillaume Leclerc, Aleksander Mądry, Josh H. McDermott
Deep neural network models of sensory systems are often proposed to learn representational transformations with invariances like those in the brain. To reveal these invariances we generated “model metamers” – stimuli whose activations within a model stage are matched to those of a natural stimulus. Metamers for…
Kaleel Mahmood, Rigel Mahmood, Ethan Rathbun, Marten van Dijk
The field of adversarial machine learning has experienced a near exponential growth in the amount of papers being produced since 2018. This massive information output has yet to be properly processed and categorized. In this paper, we seek to help alleviate this problem by systematizing the recent advances in…
Joel Dapello, Tiago Marques, Martin Schrimpf, Franziska Geiger + 2 more
Current state-of-the-art object recognition models are largely based on convolutional neural network (CNN) architectures, which are loosely inspired by the primate visual system. However, these CNNs can be fooled by imperceptibly small, explicitly crafted perturbations, and struggle to recognize objects in corrupted…
Thomas J. Rademaker, Emmanuel Bengio, Paul François
Machine learning algorithms can be fooled by small well-designed adversarial perturbations. This is reminiscent of cellular decision-making where ligands (called antagonists) prevent correct signalling, like in early immune recognition. We draw a formal analogy between neural networks used in machine learning and…
Authors not listed
Predicting reaction yields in synthetic chemistry remains a significant challenge. This study systematically evaluates the impact of tokenization, molecular representation, pre-training data, and adversarial training on a BERT-based model for yield prediction of Buchwald-Hartwig and Suzuki-Miyaura coupling reactions…
Nathan Mancheun Lui, Max D Li, Matthew Ford
Deep generative models for molecular graphs offer a new avenue for property optimization in drug discovery. Optimizing differentiable models that generate molecular graphs is certainly faster, cheaper, and much more accessible than traditional methods of chemical synthesis. Recent advances in generative modeling have…
Victor H. R. Nogueira, Rishabh Sharma, Rafael V. C. Guido, Michael J. Keiser
As efforts to improve the robustness of molecular representations advance, so does the need for methods to test and validate them. We use a Variational Auto-Encoder (VAE), an unsupervised deep learning model, to generate anomalous samples of a well-known molecular string format called SELF-referencIng Embedded Strings…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…