CoChat
Sign Up
Cited by 849Adversarial Robustness in Machine LearningEthics and Social Impacts of AIInformation and Cyber Security

The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation

Open access
Brundage, Miles, Avin, Shahar, Clark, Jack, Toner, Helen, Eckersley, Peter, Garfinkel, Ben, Dafoe, Allen, Scharre, Paul +18 more·2018·Apollo - University of Cambridge Repository
DOI 10.17863/cam.22520
Open this paper in CoChat — free accountOpen PDF

Abstract

This report surveys the landscape of potential security threats from malicious uses of AI, and proposes ways to better forecast, prevent, and mitigate these threats. After analyzing the ways in which AI may influence the threat landscape in the digital, physical, and political domains, we make four high-level recommendations for AI researchers and other stakeholders. We also suggest several promising areas for further research that could expand the portfolio of defenses, or make attacks less effective or harder to execute. Finally, we discuss, but do not conclusively resolve, the long-term equilibrium of attackers and defenders.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

DataCite · 10.17863/cam.22520

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The use of AI to automate tasks involved in surveillance, persuasion, and deception may expand threats associated with privacy invasion and social manipulation.

    “the use of AI to automate tasks involved in surveillance (e.g.analysing mass-collected data), persuasion (e.g.creating targeted propaganda), and deception (e.g.manipulating videos) may expand threats associated with privacy invasion and social manipulation”

    From Legal and human rights issues of AI: Gaps, challenges and vulnerabilities (2020) · cites this paper as Brundage et al ( 2018 )

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

No references could be resolved yet.

Research works printed but not linked: 107

  1. Abadi, M. Chu , A. Goodfellow, I. McMahan, H. Mironov, I. T alwar, K. and Zhang, L. 2016. 'Deep Learning with Differential Privacy.' In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS '16). ACM, New York, NY , USA, 308-318, https://arxiv.org/ abs/1607 .00133
  2. Abokhodair, N., Yoo, D., and McDonald, D. 2015. 'Dissecting a Social Botnet: Growth, Content and Influence in Twitter,' Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing, pp. 839851, dl.acm.org/ft\_gateway.cfm?id=2675208
  3. Adams, T. 2017 . 'AI-Powered Social Bots,' arXiv preprint server, https:/ /arxiv.org/abs/1706.05143
  4. Aker, C. and Kalkan, S. 2017 . 'Using Deep Networks for Drone Detection,' arXiv preprint server, https://arxiv.org/ abs/1706.05726 · arXiv
  5. Amodei, D. and Olah, C. et al. 2016. 'Concrete Problems in AI Safety,' arXiv preprint server, https:/ /arxiv.org/ abs/1606.06565 · arXiv
  6. Anderson, H., Woodbridge, J., and Filar, B. 2016. 'DeepDGA: Adversarially-Tuned Domain Generation and Detection,' arXiv preprint server, https:/ /arxiv.org/abs/1610.01969
  7. Anderson, H.S., Kharkar, A., Filar, B., Evans, D., and Roth, P. 2018. 'Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning,' arXiv preprint server, https://arxiv.org/abs/1801.08917 · arXiv
  8. Arulkumaran, K., Deisenroth, M., Brundage, M., and Bharath, A. 2017 . 'Deep Reinforcement Learning: A Brief Survey,' IEEE Signal Processing Magazine, Vol. 34, Issue 6, November 2017 , https://arxiv.org/abs/1708.05866 · arXiv
  9. Baier, C. and Katoen, J. 2008. Principles of Model Checking. Cambridge: MIT Press.
  10. Barberá, P., Jost, J., Nagler, J., Tucker, A., and Bonneau, R. 2015. 'Tweeting From Left to Right: Is Online Political Communication More Than an Echo Chamber?,' Psychological Science, Vol. 26, Issue 10, http:/ /journals.sagepub.com/ doi/10.1177/0956797615594620 · DOI · Paper page
  11. Bastani, O., Kim, C., Bastani, H. 2017 . 'Interpreting Blackbox Models via Model Extraction,' arXiv preprint server, https:// arxiv.org/abs/1705.08504 · arXiv
  12. Beurdouche, B., Bhargavan, K., Delignat-Lavaud, A., Fournet, C., Kohlweiss, M., Pironti, A., Strub, P., and Zinzindohoue, J. 2017. 'A messy state of the union: taming the composite state machines of TLS,' Communications of the ACM, Vol. 60, Issue 2, February 2017 , http:/ /dl.acm.org/citation.cfm?id=3023357
  13. Biggio, B., Nelson, B., and P. Laskov. 2012. 'Poisoning attacks against support vector machines,' International Conference on Machine Learning (ICML 2012), pages 1467-1474.
  14. Bostrom. 2014. Superintelligence: Paths, Dangers, Strategies. Oxford: Oxford University Press.
  15. Bryson, J., Diamantis, M., and Grant, T . 2017 . 'Of, for, and by the people: the legal lacuna of synthetic persons,' Artificial Intelligence and Law, Vol. 25, Issue 3, September 2017 , pp. 273-291.
  16. Calo, R. 2011. 'Open Robotics,' Maryland Law Review, Vol. 70, No. 3.
  17. Calo, R. 2015. 'Robotics and the Lessons of Cyberlaw,' California Law Review, Vol. 103, No. 3, pp. 513-63.
  18. Carlini, N., Mishra, P., Vaidya, T ., Zhang, Y ., Sherr, M., Shields, C., Wagner, D., and Zhou, W. 2016. 'Hidden Voice Commands,' 25th USENIX Security Symposium, people.eecs.berkeley. edu/~pratyushmishra/docs/papers/usenix16-hvc.pdf
  19. Chung, J., Jamaludin, A., and Zisserman, A. 2017 . 'You said that?,' arXiv preprint server: https:/ /arxiv.org/ abs/1705.02966 · arXiv
  20. Crawford, K. and Calo, R. 2016. 'There is a blind spot in AI research,' Nature, October 13, 2016, https://www.nature.com/ news/there-is-a-blind-spot-in-ai-research-1.20805
  21. Cummings, M. L. 2004. 'Creating Moral Buffers in Weapon Control Interface Design.' IEEE Technology and Society Magazine (Fall 2004), 29-30.
  22. D'Avino, D., Cozzolino, D., Poggi, G., and Verdoliva, L. 2017 . 'Autoencoder with recurrent neural networks for video forgery detection,' arXiv preprint, available at https:/ /arxiv.org/ abs/1708.08754 · arXiv
  23. De Choudhury, M., Counts, S., and Horvitz, E. 2013. 'Social media as a measurement tool of depression in populations,' Proceedings of the 5th Annual ACM Web Science Conference, pp. 47-56, https://dl.acm.org/citation.cfm?id=2464480
  24. Dijkstra, E.W., 1968. Letters to the editor: go to statement considered harmful. Communications of the ACM, 11(3), pp.147-148.
  25. Dinh, L., Krueger, D. and Bengio, Y ., 2014. 'NICE: Non-linear independent components estimation,' ICLR 2015 workshop paper, https://arxiv.org/abs/1410.8516 · arXiv
  26. Dowlin, N., Gilad-Bachrach, R., Laine, K., Lauter, K., Naehrig, M., and Wernsing, J. 2016. 'CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy,' Proceedings of The 33rd International Conference on Machine Learning, available online at http://proceedings. mlr.press/v48/gilad-bachrach16.html
  27. Dwork, C. and Naor, M. 1993. 'Pricing via Processing or Combatting Junk Mail.' In Brickell E.F. (eds) Advances in Cryptology - CRYPTO' 92. CRYPTO 1992. Lecture Notes in Computer Science, vol 740. Berlin: Springer.
  28. Dwork, C. 2006. 'Differential Privacy,' Proceedings of the 33rd International Colloquium on Automata, Languages and Programming, part II (ICALP 2006), available online at https:// www.microsoft.com/en-us/research/publication/differentialprivacy/
  29. Everett, R., Nurse, J., and Erola, A. 2016. 'The Anatomy of Online Deception: What Makes Automated Text Convincing?, 31st ACM/SIGAPP Symposium on Applied Computing (SAC), https://dl.acm.org/citation.cfm?id=2851813
  30. Everitt, T ., Krakovna, V., Orseau, L., Hutter, M., and Legg, S. 2017 . 'Reinforcement Learning with a Corrupted Reward Channel,' available online at https:/ /arxiv.org/abs/1705.08417
  31. Evtimov, I., Eykholt, K., Fernandes, E., Kohno, T ., Li, B., Prakash, A., Rahmati, A., and Song, D. 2017 . 'Robust PhysicalWorld Attacks on Deep Learning Models,' arXiv preprint server, https:/ /arxiv.org/abs/1707 .08945
  32. Executive Office of the President, National Science and Technology Council, Committee on Technology, 2016. 'Preparing for the Future of Artificial Intelligence,' October 2016, https://obamawhitehouse.archives.gov/ blog/2016/10/12/administrations-report-future-artificialintelligence Farquhar, S., Cotton-Barratt, O., and Snyder-Beattie, A. 2017 . 'Pricing Externalities to Balance Public Risks and Benefits of Research,' Health Security, 15:4, pages 401-408, available online at https:/ /www.ncbi.nlm.nih.gov/pubmed/28767274
  33. Filar, B., Seymour, R.J. and Park, M., 2017 . 'Ask Me Anything: A Conversational Interface to Augment Information Security Workers.' In Symposium on Usable Privacy and Security (SOUPS). https://arxiv.org/abs/1707 .05768
  34. Fisher, K. 2014. 'Using formal methods to enable more secure vehicles: DARPA's HACMS program,' ICFP '14: Proceedings of the 19th ACM SIGPLAN international conference on Functional programming. http://dl.acm.org/citation. cfm?id=2628165&CFID=776732616&CFTOKEN=19198339
  35. Fredrikson, M., Jha, S., and Ristenpart, T . 2015. 'Model inversion attacks that exploit confidence information and basic countermeasures,' in Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security. ACM, 2015, pp. 1322-1333. Available at http://doi. acm.org/10.1145/2810103.2813677 · DOI · Paper page
  36. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., WardeFarley, D., Ozair, S., Courville, A. and Bengio, Y ., 2014. 'Generative Adversarial Networks.' In Advances in Neural information Processing Systems 2014 (pp. 2672-2680), available at https:/ /arxiv.org/abs/1406.2661
  37. Goodman, B. and Flaxman, S., 2016. European Union regulations on algorithmic decision-making and a right to explanation'. arXiv preprint arXiv:1606.08813. · arXiv
  38. Gu, T., Dolan-Gavitt, B., and Garg, S. 2017 . 'BadNets: Identifying Vulnerabilities in the Machine Learning Supply Chain,' arXiv preprint available at https:/ /arxiv.org/ abs/1708.06733 · arXiv
  39. Grace, K., Salvatier, J., Dafoe, A., Zhang, B., and Evans, O. 2017. 'When Will AI Exceed Human Performance? Evidence from AI Experts,' arXiv preprint server, https:/ /arxiv.org/ abs/1705.08807 · arXiv
  40. Grosse, K., Papernot, N., Manoharan, P., Backes, M., and McDaniel, P. 2016. 'Adversarial Perturbations Against Deep Neural Networks for Malware Classification,' arXiv preprint available online at https:/ /arxiv.org/abs/1606.04435
  41. Harrison, John. 2010 'Formal Methods at Intel - An Overview.' Second NASA Formal Methods Symposium, available at https://www.cl.cam.ac.uk/~jrh13/slides/nasa-14apr10/slides. pdf
  42. Harris, E., ed. 2016. Governance of Dual-Use Technologies: Theory and Practice. American Academy of Arts and Sciences, Cambridge. Available online at http://www.amacad.org/ content/publications/publication.aspx?d=22228
  43. Hernández-Orallo, J. 2017 . The Measure of All Minds: Evaluating Natural and Artificial Intelligence. Cambridge University Press. See further details at http:/ /allminds.org/
  44. Hester, T ., Vecerik, M., Pietquin, O., Lanctot, M., Schaul, T., Piot, B., Sendonaris, A., Dulac-Arnold, G., Osband, I., Agapiou, J. and Leibo, J.Z., 2017 . 'Deep Q-learning from Demonstrations.' arXiv preprint server. https://arxiv.org/ abs/1704.03732 · arXiv
  45. Horowitz, M. 2016. 'Who'll want artificially intelligent weapons? ISIS, democracies, or autocracies?,' Bulletin of the Atomic Scientists: http://thebulletin.org/who'llwant-artificially-intelligent-weapons-isis-democracies-orautocracies9692
  46. Hosseini, H., Xiao, B. and Poovendran, R., 2017 . 'Google's Cloud Vision API Is Not Robust To Noise,' arXiv preprint server, https:/ /arxiv.org/abs/1704.05051
  47. Herley, C. 2010. 'The Plight of the Targeted Attacker in a World of Scale,' Workshop on the Economics of Information Security 2010, https://www.microsoft.com/en-us/research/ publication/the-plight-of-the-targeted-attacker-in-a-world-ofscale/
  48. IEEE Standards Association, 2017 . 'The IEEE Global Initiative for Ethical Considerations in Artificial Intelligence and Autonomous Systems,' https://standards.ieee.org/develop/ indconn/ec/autonomous\_systems.html
  49. Jaderberg, M., Mnih, V., Czarnecki, W. M., Schaul, T ., Leibo, J. Z., Silver, D., & Kavukcuoglu, K. 2016. 'Reinforcement Learning with Unsupervised Auxiliary Tasks.' arXiv preprint server. https:/ /arxiv.org/abs/1611.05397
  50. Ji, Z., Lipton, C., and Elkan, C. 2014. 'Differential privacy and machine learning: A survey and review'. In:arXiv preprint arXiv:1412.7584 · arXiv
  51. Jones, B. and Mattiacci, E. 2017 . 'A Manifesto in 140 Characters or Fewer: Social Media as a Tool of Rebel Diplomacy,' British Journal of Political Science, https:/ /www. cambridge.org/core/journals/british-journal-of-politicalscience/article/manifesto-in-140-characters-or-fewer-socialmedia-as-a-tool-of-rebel-diplomacy/82518E669A274B26E89 8A567FE22531F
  52. Jordan, M.I., and Mitchell, T .M. 2015. 'Machine learning: Trends, perspectives, and prospects,' Science Vol. 349, Issue 6245, pp. 255-260, DOI: 10.1126/science.aaa8415 · DOI · Paper page
  53. Kashyap, A., Parmar, R., Agarwal, M., Gupta, H. 2017 . 'An Evaluation of Digital Image Forgery Detection Approaches,' arXiv preprint server, https:/ /arxiv.org/abs/1703.09968
  54. Katz, G., Barrett, C., Dill, D., Julian, K., and Kochenderfer, M. 2017. 'Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks,' arXiv preprint available at https://arxiv.org/ abs/1702.01135 · arXiv
  55. Kesarwani, M., Mukhoty, B., Arya, V., and Mehta, S. 2017 . 'Model Extraction Warning in MLaaS Paradigm,' arXiv preprint server, https:/ /arxiv.org/abs/1711.07221
  56. Kharkar, A., Simecek, H., Xu, W., Evans, D. and Anderson, H. S. 2017 . 'Approaches to Evading Windows PE Malware Classifiers.' USENIX Security, 2017 .
  57. King, G., Pan, J., and Roberts, M. 2017 . 'How the Chinese Government Fabricates Social Media Posts for Strategic Distraction, not Engaged Argument,' American Political Science Review, Vol. 111, Issue 3, August 2017 , pp. 484-501, https://www.cambridge.org/core/journals/american-politicalscience-review/article/how-the-chinese-governmentfabricates-social-media-posts-for-strategic-distraction-notengaged-argument/4662DB26E2685BAF1485F14369BD137C
  58. Kirkpatrick, K. 2016. 'Battling Algorithmic Bias,' Communications of the ACM, Vol. 59, No. 10, pp. 16-17 , https://cacm.acm.org/magazines/2016/10/207759-battlingalgorithmic-bias/abstract
  59. Koh, P.W., and Liang, P. 2017 . 'Understanding Black-Box Predictions via Influence Functions,' Proceedings of ICML 2017, available online at https:/ /arxiv.org/abs/1703.04730
  60. Kosinski, M., Stillwell, D., and Graepel, T . 2013. 'Private traits and attributes are predictable from digital records of human behavior,' Proceedings of the National Academy of Sciences of the United States of America, Vol. 110, No. 15, http:/ /www. pnas.org/content/110/15/5802.full
  61. Kramer, A., Guillory, J., and Hancock, J. 2014. 'Experimental evidence of massive-scale emotional contagion through social networks.' PNAS. Vol 111, No. 24. 8788-8790. June 17 , 2014. http://www.pnas.org/content/111/24/8788.full.pdf
  62. Krimsky, S., 1982. Genetic alchemy: The social history of the recombinant DNA controversy. M.I.T. Press, Cambridge, MA.
  63. Laurie, B. and Clayton, R., 2004. 'Proof-of-work proves not to work'; version 0.2. In Workshop on Economics and Information, Security, http://www.cl.cam.ac.uk/~rnc1/ proofwork2.pdf
  64. Libicki, R. 2016. Cyberspace in Peace and War. Annapolis: Naval Institute Press.
  65. Lindell, Y . and Pinkas, B. 2009. 'Secure Multiparty Computation for Privacy-Preserving Data Mining,' The Journal of Privacy and Confidentiality, Vol. 1, No. 1, pp. 59-98, http://repository.cmu.edu/cgi/viewcontent. cgi?article=1004&context=jpc
  66. Liu, M. and Tuzel, O. 2016. 'Coupled Generative Adversarial Networks,' Proceedings of Neural Information Processing Systems (NIPS) 2016, preprint available online at https://arxiv. org/abs/1606.07536
  67. Miller, M., 2006. Robust Composition: Towards a Unified Approach to Access Control and Concurrency Control. Phd Dissertation. http:/ /www.erights.org/talks/thesis/markmthesis.pdf
  68. Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G. and Petersen, S., 2015. 'Human-level control through deep reinforcement learning,' Nature, 518(7540), pp.529-533.
  69. Moore, T. and Anderson, R. 2012. 'Internet Security.' In Peitz, M. and Waldfogel, J. (eds.) The Oxford Handbook of the Digital Economy, Oxford University Press, New York, NY , 572-599
  70. Naur, P. and Randell, B. eds., 1969. Software Engineering: Report on a conference sponsored by the NATO SCIENCE COMMITTEE, Garmisch, Germany, 7th to 11th October 1968. Nato.
  71. Naveh, A. and Tromer, E. 2016. 'PhotoProof: Cryptographic Image Authentication for Any Set of Permissible Transformations,' 2016 IEEE Symposium on Security and Privacy (SP). http://ieeexplore.ieee.org/document/7546506/
  72. NDSS. 2018. 'NDSS 2018 Call for Papers', The Network and Distributed System Security Symposium 2018. http://www. ndss-symposium.org/ndss2018/ndss-2018-call-papers/
  73. Papernot, N., McDaniel, P., Sinha, A., and Wellman, M. 2016. 'Towards the Science of Security and Privacy in Machine Learning,' available online at https:/ /arxiv.org/abs/1611.03814
  74. Papernot, N., Goodfellow, I., Sheatsley, R., Feinman, R., and McDaniel, P. 2016. 'Cleverhans v.1.0.0: an adversarial machine learning library,' arXiv preprint server, available at https:/ /arxiv. org/abs/1610.00768; associated GitHub repository available at https:/ /github.com/tensorflow/cleverhans Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z.B. and Swami, A., 2016b. 'Practical black-box attacks against deep learning systems using adversarial examples,' arXiv preprint server, https:/ /arxiv.org/abs/1602.02697
  75. Pérez-Rosas, V., Kleinberg, B., Lefevre, A., and Mihalcea, R. 2017. 'Automatic Detection of Fake News,' arXiv preprint server: https://arxiv.org/abs/1708.07104 · arXiv
  76. Quercia, D., Kosinski, M., Stillwell, D., and Crowcroft, J. 2011. 'Our Twitter Profiles, Our Selves: Predicting Personality with Twitter,' 2011 IEEE Third International Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third International Conference on Social Computing, http://ieeexplore.ieee.org/ document/6113111/
  77. Radford, A., Metz, L. and Chintala, S., 2015. 'Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,' arXiv preprint server, https://arxiv.org/ abs/1511.06434 · arXiv
  78. Rahman, M., Azimpourkivi, M., Topkara, U., Carbunar, B. 2017 . 'Video Liveness for Citizen Journalism: Attacks and Defenses,' IEEE Transactions on Mobile Computing, Vol: PP, Issue 99, http://ieeexplore.ieee.org/abstract/document/7887755/
  79. Rød, E. and Weidmann, N. 2015. 'Empowering activists or autocrats? The Internet in authoritarian regimes,' Journal of Peace Research, Vol. 52, Issue 3, http://journals.sagepub. com/doi/abs/10.1177/0022343314555782 · DOI · Paper page
  80. Rouhani, B., Riazi, M., and Koushanfar, F. 2017 . 'DeepSecure: Scalable Provably-Secure Deep Learning,' arXiv preprint server, https:/ /arxiv.org/abs/1705.08963
  81. Rubinstein, B., Nelson, B., Huang, L., Joseph, A., Lau, S., Rao, S., Taft, N., and Tygar, J.D. 2009. 'ANTIDOTE: Understanding and Defending against Poisoning of Anomaly Detectors,' Proceedings of the 9th ACM SIGCOMM Conference on Internet Measurement, pp. 1-14, https://people.eecs.berkeley. edu/~tygar/papers/SML/IMC.2009.pdf
  82. Segler, M. Preuß, M., and Waller, M. 2017 . 'Towards 'AlphaChem': Chemical Synthesis Planning with Tree Search and Deep Neural Network Policies,' arXiv preprint server, https://arxiv.org/abs/1702.00020 · arXiv
  83. Selsam, D., Liang, P., Dill, D. 2017 . 'Developing Bug-Free Machine Learning Systems with Formal Mathematics,' arXiv preprint server, https:/ /arxiv.org/abs/1706.08605
  84. Serban, I., Sankar, C., Germain, M., Zhang, S., Lin, Z., Subramanian, S., Kim, T., Pieper, M., Chandar, S., Ke, N., Rajeshwar, S., de Brebisson, A., Sotelo, J., Suhubdy, D., Michalski, V., Nguyen, A., Pineau, J., and Bengio, Y . 2017 . 'A Deep Reinforcement Learning Chatbot,' https://arxiv.org/ abs/1709.02349v2 · arXiv
  85. Seymour, J. and Tully, P. 2016. 'Weaponizing data science for social engineering: Automated E2E spear phishing on Twitter,' Black Hat conference, https://www.blackhat.com/docs/us-16/ materials/us-16-Seymour-Tully-Weaponizing-Data-ScienceFor-Social-Engineering-Automated-E2E-Spear-Phishing-OnTwitter-wp.pdf
  86. Shao, C., Ciampaglia, L., Varol, O., Flammini, A., Menczer, F. 2017. 'The spread of fake news by social bots,' arXiv preprint server, https:/ /arxiv.org/abs/1707 .07592
  87. Shokri, R., Stronati, M., and Shmatikov, V. 2016. 'Membership inference attacks against machine learning models,' CoRR, vol. abs/1610.05820, 2016. Available at http:// arxiv.org/abs/1610.05820 · arXiv
  88. Shu, K., Wang, S., Sliva, A., Tang, J., and Liu, H. 2017 . 'Fake News Detection on Social Media: A Data Mining Perspective,' arXiv preprint, https:/ /arxiv.org/abs/1708.01967
  89. Singer, P. 2009. Wired for War: The Robotics Revolution and Conflict in the 21st Century, London: Penguin Press.
  90. Šrndic, N. and Laskov, P. 2014. 'Practical Evasion of a Learning-Based Classifier: A Case Study.' In Proceedings of the 2014 IEEE Symposium on Security and Privacy, pp. 197-211. IEEE Computer Society.
  91. Stevens, R., Suciu, O., Ruef, A., Hong, S., Hicks, M., Dumitras, T. 2016. 'Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning,' Proceedings of Neural Information Processing Systems 2016, Reliable Machine Learning in the Wild workshop, https://arxiv.org/abs/1701.04739 · arXiv
  92. Sunstein, C. 2017 . #Republic: Divided Democracy in the Age of Social Media. Princeton: Princeton University Press.
  93. Standage, T. 2017 . 'Taking flight,' The Economist, http:/ /www. economist.com/technology-quarterly/2017-06-08/civiliandrones Sunderland, M., Ahn, J., Carson, C., and Kastenberg, W. 2013. 'Making Ethics Explicit: Relocating Ethics to the Core of Engineering Education,' 2013 ASEE Annual Conference.
  94. Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I. and Fergus, R., 2013. 'Intriguing properties of neural networks.' arXiv preprint server, https://arxiv.org/ abs/1312.6199 · arXiv
  95. Tambe, M. 2011. Security and Game Theory: Algorithms, Deployed Systems, and Lessons Learned. Cambridge: Cambridge University Press.
  96. Thies, J., et al. 2016. 'Face2Face: Real-time Face Capture and Reenactment of RGB Videos,' Proceedings of Computer Vision and Pattern Recognition 2016, www.graphics.stanford. edu/~niessner/papers/2016/1facetoface/thies2016face.pdf
  97. Tucker, J. (ed.). 2012. Innovation, Dual Use, and Security: Managing the Risks of Emerging Biological and Chemical Technologies. Cambridge: MIT Press.
  98. Turing, A. 1949. 'Checking a large routine,' report of a conference on High Speed Automatic Calculating Machines, pp.67-9, corrected version available online at http://www. turingarchive.org/browse.php/b/8
  99. Verma, I. 'Editorial Expression of Concern and Correction.' PNAS. Vol 111, No. 24. 10779. July 22, 2014. http://www.pnas. org/content/111/24/8788.full.pdf
  100. Vezhnevets, A.S., Osindero, S., Schaul, T ., Heess, N., Jaderberg, M., Silver, D. and Kavukcuoglu, K., 2017 . 'Feudal networks for hierarchical reinforcement learning,' arXiv preprint server, https:/ /arxiv.org/abs/1703.01161
  101. Wahby, R., Howald, M., Garg, S., shelat, a., and Walfish, M. 2016. 'Verifiable ASICs,' Security and Privacy (SP) 2016, http://ieeexplore.ieee.org/abstract/document/7546534/
  102. Woolley, S. and Howard, P. 2017 . 'Computational Propaganda Worldwide: Executive Summary.' Working Paper 2017 .11. Oxford: Project on Computational Propaganda, comprop.oii. ox.ac.uk
  103. Wright, S. 1994. Molecular politics: developing American and British regulatory policy for genetic engineering, 1972-1982. University of Chicago Press, Chicago.
  104. Yao, A.C. 1982. 'Protocols for secure computations,' 23rd Annual Symposium on Foundations of Computer Science (sfcs 1982), Chicago, IL, USA, pp. 160164. http://ieeexplore.ieee.org/stamp/stamp. jsp?tp=&arnumber=4568388&isnumber=4568364
  105. Yin, T . 2015. 'Game of Drones: Defending Against Drone Terrorism'. Texas A&M University Law Review, vol. 2, 635-673, https://ssrn.com/abstract=2944426
  106. Zeitzoff, T . 2017 . 'How Social Media Is Changing Conflict,' Journal of Conflict Resolution, 61.9 (2017): 1970-1991.
  107. Zubiaga, A., Aker, A., Bontcheva, K., Liakata, M., and Procter, R. 2017 . 'Detection and Resolution of Rumours in Social Media: A Survey,' arXiv preprint server, https://arxiv.org/ abs/1704.00656 · arXiv

Cited by

Sorted by citations

Authors
Brundage, M., Avin, S., Clark, J., Toner, H., Eckersley, P., Garfinkel, B., Dafoe, A., Scharre, P., Zeitzoff, T., Filar, B., Anderson, H., Roff, H., Allen, G., Steinhardt, J., Flynn, C., O'Heigeartaigh, S., Beard, S., Belfield, H., Farquhar, S., Lyle, C., Crootof, R., Evans, O., Page, M., Bryson, J., Yampolskiy, R., & Amodei, D.
ORCID
Venue
Apollo - University of Cambridge Repository
Publisher
Apollo - University of Cambridge Repository
Published
2018-02-20
ISSN
2331-8422 (ISSN-L)
DOI
10.17863/cam.22520
OpenAlex
W2787887017
Cited by
849
References
0
Citations by year
2026: 18 · 2025: 77 · 2024: 140 · 2023: 143 · 2022: 111 · 2021: 104 · 2020: 135 · 2019: 80 · 2018: 40
Type
posted content
Language
en
Open access
Licence
Locations
  • arXiv (Cornell University) (submittedVersion)
  • Apollo (University of Cambridge) (submittedVersion, other-oa)
  • arXiv (Cornell University)
  • Apollo
Funders
  • February Foundation
  • Silicon Valley Community Foundation (via University of Oxford)
  • Templeton World Charity Foundation (TWCF) (177155)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
  • Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
Keywords
AI security threats, threat prediction, threat prevention, threat mitigation, physical security, political manipulation, digital security

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review