Team for Research in
Ubiquitous Secure Technology

Citation
Marco Barreno, Peter L. Bartlett, Fuching Jack Chi, Anthony Joseph, Blaine Nelson, Benjamin I. Rubinstein, Udam Saini, Doug Tygar. "Open Problems in the Security of Learning". Talk or presentation, 11, November, 2008.

Abstract
Machine learning has become a valuable tool for detecting and preventing malicious activity. However, as more applications employ machine learning techniques in adversarial decision-making situations, increasingly powerful attacks become possible against machine learning systems. In this paper, we present three broad research directions towards the end of developing truly secure learning. First, we suggest that finding bounds on adversarial influence is important to understand the limits of what an attacker can and cannot do to a learning system. Second, we investigate the value of adversarial capabilities—the success of an attack depends largely on what types of information and influence the attacker has. Finally, we propose directions in technologies for secure learning and suggest lines of investigation into secure techniques for learning in adversarial environments. We intend this paper to foster discussion about the security of machine learning, and we believe that the research directions we propose represent the most important directions to pursue in the quest for secure learning.

Electronic downloads

• 17%20-%20Nelson.ppt · application/vnd.ms-powerpoint · 3716 kbytes

• HTML

  Marco Barreno, Peter L. Bartlett, Fuching Jack Chi, Anthony
  Joseph, Blaine Nelson, Benjamin I. Rubinstein, Udam Saini,
  Doug Tygar. <a
  href="http://www.truststc.org/pubs/488.html"
  ><i>Open Problems in the Security of
  Learning</i></a>, Talk or presentation,  11,
  November, 2008.

• Plain text

  Marco Barreno, Peter L. Bartlett, Fuching Jack Chi, Anthony
  Joseph, Blaine Nelson, Benjamin I. Rubinstein, Udam Saini,
  Doug Tygar. "Open Problems in the Security of
  Learning". Talk or presentation,  11, November, 2008.

• BibTeX

  @presentation{BarrenoBartlettChiJosephNelsonRubinsteinSainiTygar08_OpenProblemsInSecurityOfLearning,
      author = {Marco Barreno and Peter L. Bartlett and Fuching
                Jack Chi and Anthony Joseph and Blaine Nelson and
                Benjamin I. Rubinstein and Udam Saini and Doug
                Tygar},
      title = {Open Problems in the Security of Learning},
      day = {11},
      month = {November},
      year = {2008},
      abstract = {Machine learning has become a valuable tool for
                detecting and preventing malicious activity.
                However, as more applications employ machine
                learning techniques in adversarial decision-making
                situations, increasingly powerful attacks become
                possible against machine learning systems. In this
                paper, we present three broad research directions
                towards the end of developing truly secure
                learning. First, we suggest that finding bounds on
                adversarial influence is important to understand
                the limits of what an attacker can and cannot do
                to a learning system. Second, we investigate the
                value of adversarial capabilities—the success of
                an attack depends largely on what types of
                information and influence the attacker has.
                Finally, we propose directions in technologies for
                secure learning and suggest lines of investigation
                into secure techniques for learning in adversarial
                environments. We intend this paper to foster
                discussion about the security of machine learning,
                and we believe that the research directions we
                propose represent the most important directions to
                pursue in the quest for secure learning. },
      URL = {http://www.truststc.org/pubs/488.html}
  }
  

Posted by Jessica Gamble on 23 Jan 2009.
For additional information, see the Publications FAQ or contact webmaster at www truststc org.