08.23.19

• Overview of the Class
• Survey of the topics.
• Please the following survey for the overview (pdf)
  
• Slides (pdf)
  
• Our papers on the topic 
  
• M. Kantarcioglu, B. Xi, and C. Clifton, "Classifier evaluation and attribute selection against active adversaries," Data Min. Knowl. Discov., vol. 22, pp. 291, January 2011. (pdf)
• Y. Zhou, M. Kantarcioglu, B. Thuraisingham, and B. Xi, "Adversarial support vector machine learning" SIGKDD '12 (pdf)
• Yan Zhou, Murat Kantarcioglu, Bhavani M. Thuraisingham: Sparse Bayesian Adversarial Learning Using Relevance Vector Machine Ensembles. ICDM 2012:1206-1211 (pdf)

08.30.19

• Survey Continues
  
• Overview of the Deep Learning
• Chapters 6 Deep Learning book
  

09.06.19

• Overview of the Deep Learning
• Chapters 9 Deep Learning book

09.13.19

• Overview of Attacks Against Deep Learning
• See Our book's last Chapter

09.20.19

• Tsipras, D., Santurkar, S., Engstrom, L., Turner, A., and Madry, A. Robustness may be at odds with accuracy. In ICLR 2019.-647, 2015.  (pdf)
• Presented by Murat
  
• Schmidt, L., Santurkar, S., Tsipras, D., Talwar, K., and Madry, A. Adversarially robust generalization requires more data. In NIPS 2018.  (pdf)
  
• Presented by Murat
  
• Madry, A., Makelov, A., Schmidt, L., Tsipras, D., and Vladu, A. Towards deep learning models resistant to adversarial attacks. In ICLR 2018, Conference Track Proceedings (pdf)
  
• Presented by Murat
  

09.27.19

• Athalye, A., Carlini, N., and Wagner, D. A. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples. In ICML 2018 (pdf)
• Presented by Murat
  
• He, W., Wei, J., Chen, X., Carlini, N., and Song, D. Adversarial example defense: Ensembles of weak defenses are not strong. In 11th USENIX Workshop on Offensive Technologies, WOOT 2017. (pdf)
  Presented by Murat
  
• Trojaning Attack on Neural Networks (pdf)
• Presented by Murat
  

10.04.19

• Elsayed, G. F., Shankar, S., Cheung, B., Papernot, N., Kurakin, A., Goodfellow, I., and Sohl-Dickstein, J. Adversarial examples that fool both computer vision and time-limited humans. In NIPS 2018.  (pdf)
• Presented by Yu
  
• Eykholt, K., Evtimov, I., Fernandes, E., Li, B., Rahmati, A., Xiao, C., Prakash, A., Kohno, T., and Song, D. Robust physical-world attacks on deep learning visual classification. In IEEE CVPR June 2018. (pdf)
• Presented by Yu
  
• Carlini, N., Athalye, A., Papernot, N., Brendel, W., Rauber, J., Tsipras, D., Goodfellow, I. J., Madry, A., and Kurakin, A. On evaluating adversarial robustness. CoRR abs/1902.06705 (2019).  ICML. (pdf)
  
• Presented by  Yifan
  

10.11.19

• Sharif, M., Bhagavatula, S., Bauer, L., and Reiter, M. K. A general framework for adversarial examples with objectives. ACM Trans. Priv. Secur. 22, 3 (2019)  (pdf)
• Presented by Vibha
• Huang, S., Papernot, N., Goodfellow, I. J., Duan, Y., and Abbeel, P. Adversarial attacks on neural network policies. In ICLR 2017 Workshop Track Proceedings.  (pdf)
• Presented by Vibha
  
• Hosseini, H., and Poovendran, R. Semantic adversarial examples. In The IEEE CVPR 2018 Workshop. (pdf)
  • Presented by Yifan

10.18.19

• Carlini, N., and Wagner, D. A. Audio adversarial examples: Targeted attacks on speech-to-text. In 2018 IEEE Security and Privacy Workshops, SP Workshops 2018 (pdf)
  
• Presented by Mustafa
  
• "Discrete Adversarial Attacks and Submodular Optimization with Aplications to Text Classification" SysML (pdf)
• Presented by Pooneh
  
• Nedim Srndic and Pavel Laskov, "Alzantot, M., Sharma, Y., Elgohary, A., Ho, B.-J., Srivastava, M., and Chang, K.-W. Generating natural language adversarial examples. In EMNLP (short) (2018). (pdf) )
• Presented by Rushabh
  

10.25.19

• Qin, Y., Carlini, N., Cottrell, G. W., Goodfellow, I. J., and Raffel, C. Imperceptible, robust, and targeted adversarial examples for automatic speech recognition. In ICML 2019 (pdf)
  
• Presented by Rushabh
  
• Athalye, A., Engstrom, L., Ilyas, A., and Kwok, K. Synthesizing robust adversarial examples. In ICML 2018 (pdf)
• Presented by Pooneh
  
• Athalye, A., and Carlini, N. On the robustness of the CVPR 2018 white-box adversarial example defenses. (pdf) 
• Presented by Yu

• Carlini, N., and Wagner, D. A. Adversarial examples are not easily detected: Bypassing ten detection methods. In 10th ACM Workshop on Artificial Intelligence and Security, AISec@CCS 2017 (pdf)
  
• Presented by Pooneh
  
•  ImageNet-Trained CNNs are biased towards texture (pdf)
• Presented by Vibha
  
• Bhagoji, A. N., Chakraborty, S., Mittal, P., and Calo, S. Analyzing federated learning through an adversarial lens.  ICML 2019 (pdf) 
  • Presented by Yifan

11.08.19

• Gilmer, J., Adams, R. P., Goodfellow, I. J., Andersen, D., and Dahl, G. E. Motivating the rules of the game for adversarial example research. CoRR abs/1807.06732 (2018) (pdf)
• Presented by Rushabh
• Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks (pdf)
• Presented by Aref
  
• Programmable neural network trojan for pre-trained feature extractor (pdf)
• Presented by Aref
  

• PoTrojan: powerful neural-level trojan designs in deep learning models (pdf)
• Presented by Mustafa
  
• STRIP: A Defence Against Trojan Attacks on Deep Neural Networks (pdf)
• Presented by Aref
  
• Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks (pdf)
• Presented by Mustafa
  

11.22.19

• Project Presentations

11.29.19

• FALL BREAK

12.06.19

• Project Presentations