Skip to content

Commit 14b8982

Browse files
JungyhukJungyhuk
committed
add recent papers
1 parent a5f345a commit 14b8982

File tree

9 files changed

+99
-12
lines changed

9 files changed

+99
-12
lines changed

‎imgs/backdoor-survey.png‎

106 KB
Loading

‎imgs/backdoorl.png‎

101 KB
Loading

‎imgs/gpt-memorization.png‎

737 KB
Loading

‎imgs/imageneta.png‎

356 KB
Loading

‎imgs/imagenetr.png‎

554 KB
Loading

‎imgs/spidersyn.png‎

216 KB
Loading

‎imgs/tabor.png‎

173 KB
Loading

‎imgs/teacher-student.png‎

101 KB
Loading

‎index.html‎

Lines changed: 99 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -164,19 +164,117 @@ <h2 class="label"><a name="publications"><span >Recent Publications</span></a></
164164
</div>
165165
</form> -->
166166

167+
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
168+
<tbody><tr>
169+
<tdwidth="200"><imgsrc="imgs/imagenetr.png" border="1"width="210"></a></td>
170+
<tdwidth="20"></td>
171+
<tdvalign="middle" width="800"><pclass="content"><ahref="https://arxiv.org/abs/2006.16241"><strong>The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization</strong></a></p>
172+
<pclass="content">Dan Hendrycks, Steven Basart*, Norman Mu*, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, Justin Gilmer.</p>
173+
<pclass="content">International Conference on Computer Vision (ICCV). October, 2021.</p>
174+
<pclass="margin-small">&nbsp;</p>
175+
</tr>
176+
</tbody></table>
177+
178+
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
179+
<tbody><tr>
180+
<tdwidth="200"><imgsrc="imgs/gpt-memorization.png" border="1"width="210"></a></td>
181+
<tdwidth="20"></td>
182+
<tdvalign="middle" width="800"><pclass="content"><ahref="https://arxiv.org/abs/2012.07805"><strong>Extracting Training Data from Large Language Models</strong></a></p>
183+
<pclass="content">Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, Alina Oprea, Colin Raffel.</p>
184+
<pclass="content">USENIX Security Symposium. August, 2021.</p>
185+
<pclass="margin-small">&nbsp;</p>
186+
</tr>
187+
</tbody></table>
188+
189+
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
190+
<tbody><tr>
191+
<tdwidth="200"><imgsrc="imgs/spidersyn.png" border="1"width="210"></a></td>
192+
<tdwidth="20"></td>
193+
<tdvalign="middle" width="800"><pclass="content"><ahref="https://aclanthology.org/2021.acl-long.195/"><strong>Towards Robustness of Text-to-SQL Models against Synonym Substitution</strong></a></p>
194+
<pclass="content">Yujian Gan, Xinyun Chen, Qiuping Huang, Matthew Purver, John R. Woodward, Jinxia Xie, Pengsheng Huang.</p>
195+
<pclass="content">Annual Meeting of the Association for Computational Linguistics (ACL). August, 2021.</p>
196+
<pclass="margin-small">&nbsp;</p>
197+
</tr>
198+
</tbody></table>
199+
200+
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
201+
<tbody><tr>
202+
<tdwidth="200"><imgsrc="imgs/backdoorl.png" border="1"width="210"></a></td>
203+
<tdwidth="20"></td>
204+
<tdvalign="middle" width="800"><pclass="content"><ahref="https://arxiv.org/abs/2105.00579"><strong>BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning</strong></a></p>
205+
<pclass="content">Lun Wang, Zaynah Javed, Xian Wu, Wenbo Guo, Xinyu Xing, Dawn Song.</p>
206+
<pclass="content">International Joint Conference on Artificial Intelligence (IJCAI). August, 2021.</p>
207+
<pclass="margin-small">&nbsp;</p>
208+
</tr>
209+
</tbody></table>
210+
211+
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
212+
<tbody><tr>
213+
<tdwidth="200"><imgsrc="imgs/imageneta.png" border="1"width="210"></a></td>
214+
<tdwidth="20"></td>
215+
<tdvalign="middle" width="800"><pclass="content"><ahref="https://arxiv.org/abs/1907.07174"><strong>Natural Adversarial Examples</strong></a></p>
216+
<pclass="content">Dan Hendrycks, Kevin Zhao*, Steven Basart*, Jacob Steinhardt, Dawn Song.</p>
217+
<pclass="content">The Conference on Computer Vision and Pattern Recognition (CVPR). June, 2021.</p>
218+
<pclass="margin-small">&nbsp;</p>
219+
</tr>
220+
</tbody></table>
221+
222+
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
223+
<tbody><tr>
224+
<tdwidth="200"><imgsrc="imgs/REFIT.png" border="1"width="210"></a></td>
225+
<tdwidth="20"></td>
226+
<tdvalign="middle" width="800"><pclass="content"><ahref="https://arxiv.org/abs/1911.07205"><strong>REFIT: a Unified Watermark Removal Framework for Deep Learning Systems with Limited Data</strong></a></p>
227+
<pclass="content">Xinyun Chen*, Wenxiao Wang*, Chris Bender, Yiming Ding, Ruoxi Jia, Bo Li, Dawn Song.</p>
228+
<pclass="content">ACM Asia Conference on Computer and Communications Security (AsiaCCS). June, 2021.</p>
229+
<pclass="margin-small">&nbsp;</p>
230+
</tr>
231+
</tbody></table>
232+
233+
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
234+
<tbody><tr>
235+
<tdwidth="200"><imgsrc="imgs/teacher-student.png" border="1"width="210"></a></td>
236+
<tdwidth="20"></td>
237+
<tdvalign="middle" width="800"><pclass="content"><ahref="https://arxiv.org/abs/2102.13170"><strong>Understanding Robustness in Teacher-Student Setting: A New Perspective</strong></a></p>
238+
<pclass="content">Zhuolin Yang*, Zhaoxi Chen, Tiffany (Tianhui) Cai, Xinyun Chen, Bo Li, Yuandong Tian*.</p>
239+
<pclass="content">International Conference on Artificial Intelligence and Statistics (AISTATS). April, 2021.</p>
240+
<pclass="margin-small">&nbsp;</p>
241+
</tr>
242+
</tbody></table>
243+
244+
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
245+
<tbody><tr>
246+
<tdwidth="200"><imgsrc="imgs/backdoor-survey.png" border="1"width="210"></a></td>
247+
<tdwidth="20"></td>
248+
<tdvalign="middle" width="800"><pclass="content"><ahref="https://arxiv.org/abs/2012.10544"><strong>Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses</strong></a></p>
249+
<pclass="content">Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein.</p>
250+
<pclass="content">December, 2020.</p>
251+
<pclass="margin-small">&nbsp;</p>
252+
</tr>
253+
</tbody></table>
254+
167255
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
168256
<tbody><tr>
169257
<tdwidth="200"><imgsrc="imgs/mt_stealing.png" border="1"width="210"></a></td>
170258
<tdwidth="20"></td>
171259
<tdvalign="middle" width="800"><pclass="content"><ahref="https://arxiv.org/abs/2004.15015"><strong>Imitation Attacks and Defenses for Black-box Machine Translation Systems</strong></a></p>
172260
<pclass="content">Eric Wallace, Mitchell Stern, Dawn Song.</p>
173-
<pclass="content">arXiv preprint, 2020.</p>
261+
<pclass="content">Conference on Empirical Methods in Natural Language Processing (EMNLP), November, 2020.</p>
174262
<pclass="margin-small">&nbsp;</p>
175263
<pclass="content">
176264
<ahref="https://www.ericswallace.com/imitation">Blog</a>
177265
</p>
178266
</tbody></table>
179267

268+
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
269+
<tbody><tr>
270+
<tdwidth="200"><imgsrc="imgs/tabor.png" border="1"width="210"></a></td>
271+
<tdwidth="20"></td>
272+
<tdvalign="middle" width="800"><pclass="content"><ahref="https://ieeexplore.ieee.org/document/9338311"><strong>Towards Inspecting and Eliminating Trojan Backdoors in Deep Neural Networks</strong></a></p>
273+
<pclass="content">Wenbo Guo*, Lun Wang*, Yan Xu, Xinyu Xing, Min Du, Dawn Song.</p>
274+
<pclass="content">IEEE International Conference on Data Mining (ICDM), November, 2020.</p>
275+
<pclass="margin-small">&nbsp;</p>
276+
</tbody></table>
277+
180278
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
181279
<tbody><tr>
182280
<tdwidth="200"><imgsrc="imgs/pretrainACL.png" border="1"width="210"></a></td>
@@ -246,17 +344,6 @@ <h2 class="label"><a name="publications"><span >Recent Publications</span></a></
246344
</tr>
247345
</tbody></table>
248346

249-
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
250-
<tbody><tr>
251-
<tdwidth="200"><imgsrc="imgs/REFIT.png" border="1"width="210"></a></td>
252-
<tdwidth="20"></td>
253-
<tdvalign="middle" width="800"><pclass="content"><ahref="https://arxiv.org/abs/1911.07205"><strong>REFIT: a Unified Watermark Removal Framework for Deep Learning Systems with Limited Data</strong></a></p>
254-
<pclass="content">Xinyun Chen*, Wenxiao Wang*, Chris Bender, Yiming Ding, Ruoxi Jia, Bo Li, Dawn Song.</p>
255-
<pclass="content">ICML Workshop on Security and Privacy of Machine Learning. June, 2019.</p>
256-
<pclass="margin-small">&nbsp;</p>
257-
</tr>
258-
</tbody></table>
259-
260347
<tableborder="0" cellpadding="0" cellspacing="15" width="100%">
261348
<tbody><tr>
262349
<tdwidth="200"><imgsrc="imgs/RL_privacy.png" border="1"width="210"></a></td>

0 commit comments

Comments
(0)