responsible_xai.bib

@article{fair_washing,
	title = {Fairwashing: the {R}isk of {R}ationalization},
	author = {A{\"\i}vodji, Ulrich and Arai, Hiromi and Fortineau, Olivier and Gambs, S{\'e}bastien and Hara, Satoshi and Tapp, Alain},
	journal = {arXiv preprint arXiv:1901.09749},
	year = {2019}, 
	note = {URL: \url{https://arxiv.org/pdf/1901.09749.pdf}}}

@inproceedings{modeltracker,
	title={Modeltracker: {R}edesigning {P}erformance {A}nalysis {T}ools for {M}achine {L}earning},
  	author={Amershi, Saleema and Chickering, Max and Drucker, Steven M. and Lee, Bongshin and Simard, Patrice and Suh, Jina},
 	 booktitle={Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems},
 	 pages={337--346},
 	 year={2015},
 	 organization={ACM},
	 note={URL: \url{https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/amershi.CHI2015.ModelTracker.pdf}}}

@inproceedings{grad_attr,
 	title={Towards {B}etter {U}nderstanding of {G}radient-based {A}ttribution {M}ethods for {D}eep {N}eural {N}etworks},
 	author={Ancona, Marco and Ceolini, Enea and Oztireli, Cengiz and Gross, Markus},
 	booktitle={6th International Conference on Learning Representations (ICLR 2018)},
 	note={URL: \url{https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/249929/Flow_ICLR_2018.pdf}},
 	year={2018}}

@article{angwin16,
	Author = {Julia Angwin and Jeff Larson and Surya Mattu and Lauren Kirchner},
	Journal = {ProPublica},
	Title = {{M}achine {B}ias: {T}here's {S}oftware {U}sed {A}cross the {C}ountry to {P}redict {F}uture {C}riminals. {A}nd {I}t's {B}iased {A}gainst {B}lacks.},
	note = {URL: \url{https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing}},
	Year = {2016}}

@article{ale_plot,
 	title = {Visualizing the {E}ffects of {P}redictor {V}ariables in {B}lack {B}ox {S}upervised {L}earning {M}odels},
 	author = {Apley, Daniel W.},
 	journal = {arXiv preprint arXiv:1612.08468},
 	year = {2016},
	note = {URL: \url{https://arxiv.org/pdf/1612.08468.pdf}}}

@article{dt_surrogate2,
	title = {Interpreting {B}lackbox {M}odels via {M}odel {E}xtraction},
	author ={Osbert Bastani and Carolyn Kim and Hamsa Bastani},
	journal = {arXiv preprint arXiv:1705.08504},
	note = {URL: \url{https://arxiv.org/pdf/1705.08504.pdf}},
	year = {2017}}

@inproceedings{viper,
	title={Verifiable {R}einforcement {L}earning {V}ia {P}olicy {E}xtraction},
 	author={Bastani, Osbert and Pu, Yewen and Solar-Lezama, Armando},
	booktitle={Advances in Neural Information Processing Systems},
	pages={2494--2504},
  	year={2018},
	note={URL: \url{http://papers.nips.cc/paper/7516-verifiable-reinforcement-learning-via-policy-extraction.pdf}}}
	
@article{dt_surrogate1,
	Author = {Mark W. Craven and Jude W. Shavlik},
	Journal = {Advances in Neural Information Processing Systems},
	Title = {Extracting {T}ree-{S}tructured {R}epresentations of {T}rained {N}etworks},
	note={URL: \url{http://papers.nips.cc/paper/1152-extracting-tree-structured-representations-of-trained-networks.pdf}},
	Year = {1996}}

@article{been_kim1,
	Author = {Finale Doshi-Velez and Been Kim},
	Title = {Towards a {R}igorous {S}cience of {I}nterpretable {M}achine {L}earning},
	Journal = {arXiv preprint arXiv:1702.08608},
	note = {URL: \url{https://arxiv.org/pdf/1702.08608.pdf}},
	Year = {2017}}

@inproceedings{dwork2012fairness,
	title={Fairness {T}hrough {A}wareness},
  	author={Dwork, Cynthia and Hardt, Moritz and Pitassi, Toniann and Reingold, Omer and Zemel, Richard},
  	booktitle={Proceedings of the 3rd Innovations in Theoretical Computer Science Conference},
  	pages={214--226},
  	year={2012},
  	organization={ACM}, 
	note={URL: \url{https://arxiv.org/pdf/1104.3913.pdf}}}

@inproceedings{feldman2015certifying,
  	title={Certifying and {R}emoving {D}isparate {I}mpact},
  	author={Feldman, Michael and Friedler, Sorelle A. and Moeller, John and Scheidegger, Carlos and Venkatasubramanian, Suresh},
 	 booktitle={Proceedings of the 21\textsuperscript{st} ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  	pages={259--268},
  	year={2015},
  	organization={ACM},
	note={URL: \url{https://arxiv.org/pdf/1412.3756.pdf}}}
		
@article{flores2016false,
	title={False {P}ositives, {F}alse {N}egatives, and {F}alse {A}nalyses: {A} {R}ejoinder to {M}achine {B}ias: {T}here's {S}oftware {U}sed across the {C}ountry to {P}redict {F}uture {C}riminals. {A}nd {I}t's {B}iased against {B}lacks},
	author={Flores, Anthony W. and Bechtel, Kristin and Lowenkamp, Christopher T.},
	journal={Fed. Probation},
	volume={80},
	pages={38},
	year={2016},
	publisher={HeinOnline}, 
	note={URL: \url{https://bit.ly/2Gesf9Y}}}			
		
@book{esl,
	Address = {New York},
	Author = {Jerome Friedman and Trevor Hastie and Robert Tibshirani},
	Booktitle = {\textit{The Elements of Statistical Learning}},
	Publisher = {Springer},
	Title = {\textbf{The Elements of Statistical Learning}},
	note = {URL: \url{https://web.stanford.edu/~hastie/ElemStatLearn/printings/ESLII\_print12.pdf}},
	Year = {2001}}
		
@article{gilpin2018explaining,
	title = {Explaining {E}xplanations: {A}n {A}pproach to {E}valuating {I}nterpretability of {M}achine {L}earning},
	author = {Leilani H. Gilpin and David Bau and Ben Z. Yuan and Ayesha Bajwa and Michael Specter and Lalana Kagal},
	journal = {arXiv preprint arXiv:1806.00069},
	note = {URL: \url{https://arxiv.org/pdf/1806.00069.pdf}},
	year = {2018}}
	
@article{ice_plots,
	Author = {Alex Goldstein and Adam Kapelner and Justin Bleich and Emil Pitkin},
	Journal = {Journal of Computational and Graphical Statistics},
	Number = {1},
	Title = {Peeking {I}nside the {B}lack {B}ox: {V}isualizing {S}tatistical {L}earning with {P}lots of {I}ndividual {C}onditional {E}xpectation},
	Volume = {24},
	Year = {2015},
	note = {URL: \url{https://arxiv.org/pdf/1309.6392.pdf}}}

@misc{gopinathan1998fraud,
	title = {Fraud {D}etection using {P}redictive {M}odeling},
	author = {Gopinathan, Krishna M. and Biafore, Louis S. and Ferguson, William M. and Lazarus, Michael A. and Pathria, Anu K. and Jost, Allen},
	year = {1998},
	month = oct # "~6",
	publisher = {Google Patents},
	note = {US Patent 5,819,226. URL: \url{https://patents.google.com/patent/US5819226A}}}

@article{guidotti2018survey,
	title = {{A} {S}urvey of {M}ethods for {E}xplaining {B}lack {B}ox {M}odels},
	author = {Guidotti, Riccardo and Monreale, Anna and Ruggieri, Salvatore and Turini, Franco and Giannotti, Fosca and Pedreschi, Dino},
	journal = {ACM Computing Surveys (CSUR)},
	volume = {51},
	number = {5},
	pages = {93},
	year = {2018},
	publisher = {ACM},
	note = {URL: \url{https://arxiv.org/pdf/1802.01933.pdf}}}

@inproceedings{art_and_sci,
	title = {On the {A}rt and {S}cience of {M}achine {L}earning {E}xplanations},
	author = {Hall, Patrick},
	booktitle={KDD '19 XAI Workshop Proceedings},
	note = {URL: \url{https://arxiv.org/pdf/1810.02909.pdf}},
	year = {2019}}

@inproceedings{hardt2016equality,
  	title={Equality of {O}pportunity in {S}upervised {L}earning},
  	author={Hardt, Moritz and Price, Eric and Srebro, Nati and others},
  	booktitle={Advances in Neural Information Processing Systems},
  	pages={3315--3323},
  	year={2016},
	note={URL: \url{http://papers.nips.cc/paper/6374-equality-of-opportunity-in-supervised-learning.pdf}}}

@article{lime-sup,
	title = {Locally {I}nterpretable {M}odels and {E}ffects {B}ased on {S}upervised {P}artitioning ({LIME-SUP})},
	author = {Linwei Hu and Jie Chen and Vijayan N. Nair and Agus Sudjianto},
	journal = {arXiv preprint arXiv:1806.00663},
	note = {URL: \url{https://arxiv.org/ftp/arxiv/papers/1806/1806.00663.pdf}},
	year = {2018}}

@article{kamiran2012data,
 	title={Data {P}reprocessing {T}echniques for {C}lassification {W}ithout {D}iscrimination},
  	author={Kamiran, Faisal and Calders, Toon},
 	journal={Knowledge and Information Systems},
  	volume={33},
  	number={1},
  	pages={1--33},
  	year={2012},
  	publisher={Springer},
	note={URL: \url{https://bit.ly/2lH95lQ}}}

@misc{kangdebugging,
  	title={Debugging {M}achine {L}earning {M}odels via {M}odel {A}ssertions},
  	author={Kang, Daniel and Raghavan, Deepti and Bailis, Peter and Zaharia, Matei},
	year={2019},
	note={URL: \url{https://www-cs.stanford.edu/~matei/papers/2018/mlsys_model_assertions.pdf}}}

@article{keinan2004fair,
	title = {Fair {A}ttribution of {F}unctional {C}ontribution in {A}rtificial and {B}iological {N}etworks},
	author = {Keinan, Alon and Sandbank, Ben and Hilgetag, Claus C. and Meilijson, Isaac and Ruppin, Eytan},
	journal = {Neural Computation},
	volume = {16},
	number = {9},
	pages = {1887--1915},
	year = {2004},
	publisher = {MIT Press},
	note={URL: \url{http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.436.6801&rep=rep1&type=pdf}}}

@misc{uci,
 	author = {M. Lichman},
  	year = {2013},
  	title = {{UCI} {M}achine {L}earning {R}epository},
  	note = {URL: \url{http://archive.ics.uci.edu/ml}},
  	institution = {University of California, Irvine, School of Information and Computer Sciences"}}

@article{lipovetsky2001analysis,
  	title={Analysis of {R}egression in {G}ame {T}heory {A}pproach},
  	author={Lipovetsky, Stan and Conklin, Michael},
  	journal={Applied Stochastic Models in Business and Industry},
  	volume={17},
  	number={4},
  	pages={319--330},
  	year={2001},
  	publisher={Wiley Online Library}}

@article{lipton1,
	title = {The {M}ythos of {M}odel {I}nterpretability},
	author = {Lipton, Zachary C.},
	journal = {arXiv preprint arXiv:1606.03490},
	year = {2016},
	note = {URL: \url{https://arxiv.org/pdf/1606.03490.pdf}}}

@incollection{tree_shap,
	title = {Consistent {I}ndividualized {F}eature {A}ttribution for {T}ree {E}nsembles},
	author = {Lundberg, Scott M. and Erion, Gabriel G. and Lee, Su-In},
	booktitle = {Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017)},
	pages = {15--21},
	editor = {Been Kim and Dmitry M. Malioutov and Kush R. Varshney and Adrian Weller},
	year = {2017},
	note = {URL: \url{https://openreview.net/pdf?id=ByTKSo-m-}},
	publisher = {ICML WHI 2017},
	organization = {ICML}}

@incollection{shapley,
	title = {A {U}nified {A}pproach to {I}nterpreting {M}odel {P}redictions},
	author = {Lundberg, Scott M. and Lee, Su-In},
	booktitle = {Advances in Neural Information Processing Systems 30},
	editor = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
	pages = {4765--4774},
	year = {2017},
	publisher = {Curran Associates, Inc.},
	note = {URL: \url{http://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions.pdf}}}

@book{molnar,
	title = {\textbf{\textit{{I}nterpretable {M}achine {L}earning}}},
	author = {Christoph Molnar},
	publisher = {christophm.github.io},
	note = {URL: \url{https://christophm.github.io/interpretable-ml-book/}},
	year = {2018}}
	
@article{murdoch2019interpretable,
	title={Interpretable {M}achine {L}earning: {D}efinitions, {M}ethods, and {A}pplications},
	author={Murdoch, W. James and Singh, Chandan and Kumbier, Karl and Abbasi-Asl, Reza and Yu, Bin},
	journal={arXiv preprint arXiv:1901.04592},
	year={2019}, 
	note={URL: \url{https://arxiv.org/pdf/1901.04592.pdf}}}	
	
@inproceedings{lime,
	title = {Why {S}hould {I} {T}rust {Y}ou?: {E}xplaining the {P}redictions of {A}ny {C}lassifier},
	author = {Marco Tulio Ribeiro and Sameer Singh and Carlos Guestrin},
	booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
	pages = {1135--1144},
	year = {2016},
	note = {URL: \url{http://www.kdd.org/kdd2016/papers/files/rfp0573-ribeiroA.pdf}},
	organization = {ACM}}

@article{please_stop,
 	title = {Please {S}top {E}xplaining {B}lack {B}ox {M}odels for {H}igh {S}takes {D}ecisions},
 	author = {Rudin, Cynthia},
  	note = {URL: \url{https://arxiv.org/pdf/1811.10154.pdf}},
  	journal = {arXiv preprint arXiv:1811.10154},
  	year = {2018}}

@book{shapley1988shapley,
	title = {\textit{The Shapley value: {E}ssays in honor of {L}loyd {S}. {S}hapley}},
	author = {Shapley, Lloyd S. and Roth, Alvin E. and others},
	year = {1988},
	publisher = {Cambridge University Press},
	note = {URL: \url{http://www.library.fa.ru/files/Roth2.pdf}}}

@article{shokri2019privacy,
  	title={Privacy {R}isks of {E}xplaining {M}achine {L}earning {M}odels},
   	author={Shokri, Reza and Strobel, Martin and Zick, Yair},
  	journal={arXiv preprint arXiv:1907.00164},
  	year={2019},
	note={URL:\url{https://arxiv.org/pdf/1907.00164.pdf}}}

@inproceedings{membership_inference,
 	title={Membership {I}nference {A}ttacks {A}gainst {M}achine {L}earning {M}odels},
 	author={Shokri, Reza and Stronati, Marco and Song, Congzheng and Shmatikov, Vitaly},
 	booktitle={2017 IEEE Symposium on Security and Privacy (SP)},
 	pages={3--18},
 	year={2017},
 	organization={IEEE}, 
	note={URL: \url{https://arxiv.org/pdf/1610.05820.pdf}}}	

@article{kononenko2010efficient,
	title = {An {E}fficient {E}xplanation of {I}ndividual {C}lassifications using {G}ame {T}heory},
	author = {Strumbelj, Erik and Kononenko, Igor},
	journal = {Journal of Machine Learning Research},
	volume = {11},
	number = {Jan},
	pages = {1--18},
	year = {2010},
	note = {URL: \url{http://www.jmlr.org/papers/volume11/strumbelj10a/strumbelj10a.pdf}}}

@inproceedings{model_stealing,
	title={Stealing {M}achine {L}earning {M}odels via {P}rediction {A}{P}{I}s},
	author={Tram{\`e}r, Florian and Zhang, Fan and Juels, Ari and Reiter, Michael K. and Ristenpart, Thomas},
	booktitle={25th $\{$USENIX$\}$ Security Symposium ($\{$USENIX$\}$ Security 16)},
	pages={601--618},
	year={2016},
	note={URL: \url{https://www.usenix.org/system/files/conference/usenixsecurity16/sec16_paper_tramer.pdf}}}

@article{slim,
	Author = {Ustun, Berk and Rudin, Cynthia},
	Journal = {Machine Learning},
	Number = {3},
	Pages = {349--391},
	Publisher = {Springer},
	Title = {{Supersparse {L}inear {I}nteger {M}odels for {O}ptimized {M}edical {S}coring {S}ystems}},
	Volume = {102},
	note={URL: \url{https://users.cs.duke.edu/~cynthia/docs/UstunTrRuAAAI13.pdf}},
	Year = {2016}}

@article{wf_xnn,
	title = {Explainable {N}eural {N}etworks {B}ased on {A}dditive {I}ndex {M}odels},
	author = {Vaughan, Joel and Sudjianto, Agus and Brahimi, Erind and Chen, Jie and Nair, Vijayan N.},
	journal = {arXiv preprint arXiv:1806.01933},
	note = {URL: \url{https://arxiv.org/pdf/1806.01933.pdf}},
	year = {2018}}

@article{weller2017challenges,
	title = {{C}hallenges for {T}ransparency},
	author = {Weller, Adrian},
	journal = {arXiv preprint arXiv:1708.01870},
	year = {2017},
	note = {URL: \url{https://arxiv.org/pdf/1708.01870.pdf}}}

@book{ff_interpretability,
	author = {Williams, Mike and others},
  	title = {Interpretability},
  	publisher = {Fast Forward Labs},
  	year = {2017},
  	note = {URL: \url{https://www.cloudera.com/products/fast-forward-labs-research.html}}}

@inproceedings{sbrl,
  	title = {Scalable {B}ayesian {R}ule {L}ists},
  	author = {Hongyu Yang and Cynthia Rudin and Margo Seltzer},
  	booktitle = {Proceedings of the 34th International Conference on Machine Learning {(ICML)}},
  	note = {URL: \url{https://arxiv.org/pdf/1602.08610.pdf}},
  	year = {2017}}
	
@inproceedings{zhang2018mitigating,
  	title={Mitigating {U}nwanted {B}iases with {A}dversarial {L}earning},
  	author={Zhang, Brian Hu and Lemoine, Blake and Mitchell, Margaret},
  	booktitle={Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society},
  	pages={335--340},
  	year={2018},
  	organization={ACM}, 
	note={URL: \url{https://arxiv.org/pdf/1801.07593.pdf}}}