Merge pull request #51 from gfw-report/master

Add ten FOCI'24 issue 2 papers, two PETS'24 papers, and support accent characters in cite names.

references.bib

@@ -7,6 +7,118 @@
 	url = {https://www.cs-pk.com/sec24-spotproxy-final.pdf},
 }
 
+@article{Vines2024c,
+	author = {Paul Vines and Samuel McKay and Jesse Jenter and Suresh Krishnaswamy},
+	title = {Communication Breakdown: Modularizing Application Tunneling for Signaling Around Censorship},
+	journal = {Privacy Enhancing Technologies},
+	volume = {2024},
+	number = {1},
+	publisher = {},
+	year = {2024},
+	url = {https://petsymposium.org/popets/2024/popets-2024-0027.pdf},
+}
+
+@article{Tang2024a,
+	author = {Jenny Tang and Léo Alvarez and Arjun Brar and Nguyen Phong Hoang and Nicolas Christin},
+	title = {Automatic Generation of Web Censorship Probe Lists},
+	journal = {Privacy Enhancing Technologies},
+	volume = {2024},
+	number = {4},
+	publisher = {},
+	year = {2024},
+	url = {https://petsymposium.org/popets/2024/popets-2024-0106.pdf},
+}
+
+@inproceedings{Ahmed2024a,
+	author = {Mohamed Ahmed and Jeffrey Knockel},
+	title = {Extended Abstract: The Impact of Online Censorship on {LLMs}},
+	booktitle = {Free and Open Communications on the Internet},
+	publisher = {},
+	year = {2024},
+	url = {https://www.petsymposium.org/foci/2024/foci-2024-0006.pdf},
+}
+
+@inproceedings{Gao2024a,
+	author = {Tianyu Gao and Ping Ji},
+	title = {Extended Abstract: Leveraging Large Language Models to Identify {Internet} Censorship through Network Data},
+	booktitle = {Free and Open Communications on the Internet},
+	publisher = {},
+	year = {2024},
+	url = {https://www.petsymposium.org/foci/2024/foci-2024-0007.pdf},
+}
+
+@inproceedings{Calle2024a,
+	author = {Paola Calle and Larissa Savitsky and Arjun Nitin Bhagoji and Nguyen Phong Hoang and Shinyoung Cho},
+	title = {Toward Automated {DNS} Tampering Detection Using Machine Learning},
+	booktitle = {Free and Open Communications on the Internet},
+	publisher = {},
+	year = {2024},
+	url = {https://www.petsymposium.org/foci/2024/foci-2024-0008.pdf},
+}
+
+@inproceedings{Pu2024a,
+	author = {Michael Pu and Andrew Wang and Anthony Chang and Kieran Quan and Yi Wei Zhou},
+	title = {Exploring {Amazon} Simple Queue Service ({SQS}) for Censorship Circumvention},
+	booktitle = {Free and Open Communications on the Internet},
+	publisher = {},
+	year = {2024},
+	url = {https://www.petsymposium.org/foci/2024/foci-2024-0009.pdf},
+}
+
+@inproceedings{Vilalonga2024a,
+	author = {Afonso Vilalonga and João S. Resende and Henrique Domingos},
+	title = {Looking at the Clouds: Leveraging Pub/Sub Cloud Services for Censorship-Resistant Rendezvous Channels},
+	booktitle = {Free and Open Communications on the Internet},
+	publisher = {},
+	year = {2024},
+	url = {https://www.petsymposium.org/foci/2024/foci-2024-0010.pdf},
+}
+
+@inproceedings{Vines2024b,
+	author = {Paul Vines},
+	title = {Ten Years Gone: Revisiting Cloud Storage Transports to Reduce Censored User Burdens},
+	booktitle = {Free and Open Communications on the Internet},
+	publisher = {},
+	year = {2024},
+	url = {https://www.petsymposium.org/foci/2024/foci-2024-0011.pdf},
+}
+
+@inproceedings{Müller2024a,
+	author = {Philipp Müller and Niklas Niere and Felix Lange and Juraj Somorovsky},
+	title = {Turning Attacks into Advantages: Evading {HTTP} Censorship with {HTTP} Request Smuggling},
+	booktitle = {Free and Open Communications on the Internet},
+	publisher = {},
+	year = {2024},
+	url = {https://www.petsymposium.org/foci/2024/foci-2024-0012.pdf},
+}
+
+@inproceedings{Hanlon2024a,
+	author = {Michelina Hanlon and Gerry Wan and Anna Ascheman and Zakir Durumeric},
+	title = {Detecting {VPN} Traffic through Encapsulated {TCP} Behavior},
+	booktitle = {Free and Open Communications on the Internet},
+	publisher = {},
+	year = {2024},
+	url = {https://www.petsymposium.org/foci/2024/foci-2024-0016.pdf},
+}
+
+@inproceedings{Kujath2024a,
+	author = {Beau Kujath and Jeffrey Knockel and Paul Aguilar and Diego Morabito and Masashi Crete-Nishihata and Jedidiah R. Crandall},
+	title = {Analyzing Prominent Mobile Apps in {Latin America}},
+	booktitle = {Free and Open Communications on the Internet},
+	publisher = {},
+	year = {2024},
+	url = {https://www.petsymposium.org/foci/2024/foci-2024-0017.pdf},
+}
+
+@inproceedings{Ruo2024a,
+	author = {Samuel Ruo and Jeffrey Knockel and Zoë Reichert},
+	title = {Lost in Translation: Characterizing Automated Censorship in Online Translation Services},
+	booktitle = {Free and Open Communications on the Internet},
+	publisher = {},
+	year = {2024},
+	url = {https://www.petsymposium.org/foci/2024/foci-2024-0018.pdf},
+}
+
 @inproceedings{Wang2024a,
 	author     = {Chenxu Wang and Jiangyi Yin and Zhao Li and Hongbo Xu and Zhongyi Zhang and Qingyun Liu},
 	title      = {Identifying {VPN} Servers through Graph-Represented Behaviors},
@@ -604,7 +716,7 @@
 }
 
 @inproceedings{Padmanabhan2021a,
-	author = {Ramakrishna Padmanabhan and and Arturo Filastò and Maria Xynou and Ram Sundara Raman and Kennedy Middleton and Mingwei Zhang and Doug Madory and Molly Roberts and Alberto Dainotti},
+	author = {Ramakrishna Padmanabhan and Arturo Filastò and Maria Xynou and Ram Sundara Raman and Kennedy Middleton and Mingwei Zhang and Doug Madory and Molly Roberts and Alberto Dainotti},
 	title = {A multi-perspective view of {Internet} censorship in {Myanmar}},
 	booktitle = {Free and Open Communications on the Internet},
 	publisher = {ACM},

src/go.mod

@@ -2,4 +2,4 @@ module censorbib-go
 
 go 1.21.3
 
-require github.com/nickng/bibtex v1.3.0
+require github.com/nickng/bibtex v1.4.0

src/go.sum

@@ -1,2 +1,2 @@
-github.com/nickng/bibtex v1.3.0 h1:iv0408z8Xe+FEVquJUo8eraXnhrAF0e+2/WayPcism8=
-github.com/nickng/bibtex v1.3.0/go.mod h1:4BJ3ka/ZjGVXcHOlkzlRonex6U17L3kW6ICEsygP2bg=
+github.com/nickng/bibtex v1.4.0 h1:c5lcFG8RSXE0LrxAlkj9jHpYhzgLLKn2feyrUmiIz8A=
+github.com/nickng/bibtex v1.4.0/go.mod h1:4BJ3ka/ZjGVXcHOlkzlRonex6U17L3kW6ICEsygP2bg=

src/main.go

@@ -13,8 +13,9 @@ import (
 	"github.com/nickng/bibtex"
 )
 
-// Matches e.g.: @inproceedings{Doe2024a,
-var re = regexp.MustCompile(`@[a-z]*\{([A-Za-z\-]*[0-9]{4}[a-z]),`)
+// Matches e.g.: @inproceedings{Müller2024a,
+// \p{L}\p{M} matches any letter, including accented characters.
+var re = regexp.MustCompile(`@[a-z]*\{([\"\p{L}\p{M}\-]*[0-9]{4}[a-z]),`)
 
 // Map a cite name (e.g., Doe2024a) to its line number in the .bib file. All
 // cite names are unique.

src/vendor/github.com/nickng/bibtex/token.go

@@ -29,8 +29,18 @@ func isWhitespace(ch rune) bool {
 	return ch == ' ' || ch == '\t' || ch == '\n' || ch == '\r'
 }
 
+func isAccent(ch rune) bool {
+	accents := "äöüßéêçñÁÉÍÓÚáéíóúàèìòùâêîôûãõñÄÖÜ"
+	for _, accent := range accents {
+		if ch == accent {
+			return true
+		}
+	}
+	return false
+}
+
 func isAlpha(ch rune) bool {
-	return ('a' <= ch && ch <= 'z') || ('A' <= ch && ch <= 'Z')
+	return ('a' <= ch && ch <= 'z') || ('A' <= ch && ch <= 'Z') || isAccent(ch)
 }
 
 func isDigit(ch rune) bool {

src/vendor/modules.txt

@@ -1,3 +1,3 @@
-# github.com/nickng/bibtex v1.3.0
+# github.com/nickng/bibtex v1.4.0
 ## explicit; go 1.18
 github.com/nickng/bibtex