Adversarial label flips attack on support vector machines

Frontiers in Artificial Intelligence and Applications

Volumn 242, Issue , 2012, Pages 870-875

  Xiao, Han ^a   Xiao, Huang ^a   Eckert, Claudia ^a  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

CLASSIFICATION ALGORITHM; CLASSIFICATION ERRORS; OPTIMIZATION FRAMEWORK; ROBUST CLASSIFICATION; SUPPORT VECTORS MACHINE; TRAINING SETS;

SUPPORT VECTOR MACHINES;

EID: 84878781560     PISSN: 09226389     EISSN: 18798314     Source Type: Book Series    
DOI: 10.3233/978-1-61499-098-7-870     Document Type: Conference Paper

References (14)

1. M. Barreno, B. Nelson, A.D. Joseph, and JD Tygar, 'The security of machine learning', Machine Learning, 81(2), 121-148, (2010).
2. B. Biggio, B. Nelson, and B. Laskov, 'Support vector machines under adversarial label noise', in Proc. of 3rd ACML, pp. 97-112, (2011).
3. O. Chapelle, B. Schölkopf, A. Zien, et al., Semi-supervised learning, MIT Press, 2006.
4. O. Dekel and O. Shamir, 'Learning to classify with missing and corrupted features', in Proc. of 25th ICML, pp. 216-223, (2008).
5. O. Dekel and O. Shamir, 'Good learners for evil teachers', in Proc. of 26th ICML, pp. 233-240. ACM, (2009).
6. A. Globerson and S. Roweis, 'Nightmare at test time: robust learning by feature deletion', in Proc. of 23rd ICML, pp. 353-360. ACM, (2006).
7. M. Kearns and M. Li, 'Learning in the presence of malicious errors', in Proc. of 20th STOC, pp. 267-280. ACM, (1988).
8. A.R. Klivans, P.M. Long, and R.A. Servedio, 'Learning halfspaces with malicious noise', JMLR, 10, 2715-2740, (2009).
9. D. Lowd and C. Meek, 'Adversarial learning', in Proc. of 11th SIGKDD, pp. 641-647. ACM, (2005).
10. D. Lowd and C. Meek, 'Good word attacks on statistical spam filters', in Proc. of 2nd Conference on Email and Anti-Spam, pp. 125-132, (2005).
11. B. Nelson, M. Barreno, F.J. Chi, A.D. Joseph, B.I.P. Rubinstein, U. Saini, C. Sutton, JD Tygar, and K. Xia, 'Exploiting machine learning to subvert your spam filter', in Proc. of the 1st Usenix Workshop on Large-Scale Exploits and Emergent Threats, p. 7, (2008).
12. J. Newsome, B. Karp, and D. Song, 'Paragraph: Thwarting signature learning by training maliciously', in Recent Advances in Intrusion Detection, pp. 81-105. Springer, (2006).
13. L. Vicente, G. Savard, and J. Júdice, 'Descent approaches for quadratic bilevel programming', Journal of Optimization Theory and Applications, 81(2), 379-399, (1994).
14. Han Xiao, T. Stibor, and C. Eckert, 'Evasion attack of multi-class linear classifiers', in Proc. of 16th PAKDD, pp. 207-218, (2012).