Taesung Lee

38 papers A* 4A 2B 2Journal 15Unranked 15
YearRankTypeTitle / Venue / Authors
2025 J jnl
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming.
CoRR
Mrinank Sharma, Meg Tong, Jesse Mu, Jerry Wei, Jorrit Kruthoff, Scott Goodfriend, Euan Ong, Alwin Peng, Raj Agarwal, Cem Anil, Amanda Askell, Nathan Bailey, Joe Benton, Emma Bluemke, Samuel R. Bowman, Eric Christiansen, Hoagy Cunningham, Andy Dau, Anjali Gopal, Rob Gilson, Logan Graham, Logan Howard, Nimit Kalra, Taesung Lee, Kevin Lin, Peter Lofgren, Francesco Mosconi, Clare O'Hara, Catherine Olsson, Linda Petrini, Samir Rajani, Nikhil Saxena, Alex Silverstein, Tanya Singh, Theodore R. Sumers, Leonard Tang, Kevin K. Troy, Constantin Weisser, Ruiqi Zhong, Giulio Zhou, Jan Leike, Jared Kaplan, Ethan Perez
2025 J jnl
Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuning.
CoRR
Shambhavi Krishna, Atharva Naik, Chaitali Agarwal, Sudharshan Govindan, Taesung Lee, Haw-Shiuan Chang
2024 — conf
13.3 A 280-Layer 1Tb 4b/cell 3D-NAND Flash Memory with a 28.5Gb/mm2 Areal Density and a 3.2GB/s High-Speed IO Rate.
ISSCC
Wontaeck Jung, Hyunggon Kim, Do-Bin Kim, Tae-Hyun Kim, Nam-Hee Lee, Dongjin Shin, Minyoung Kim, Youngsik Rho, Hun-Jong Lee, Yujin Hyun, Jaeyoung Park, Taekyung Kim, Hwiwon Kim, Gyeongwon Lee, Jisang Lee, Joonsuc Jang, Jungmin Park, Sion Kim, Su Chang Jeon, Suyong Kim, Jung-Ho Song, Min-Seok Kim, Taesung Lee, Byung-Kwan Chun, Tongsung Kim, Young Gyu Lee, Hokil Lee, Soowoong Lee, Hwaseok Lee, Dooho Cho, Sangwan Nam, Yeomyung Kim, Kunyong Yoon, Yoonjae Lee, Sunghoon Kim, Jungseok Hwang, Raehyun Song, Hyunsik Jang, Jae-Ick Son, Hongsoo Jeon, Myunghun Lee, Mookyung Lee, Kisung Kim, Eungsuk Lee, Myeong-Woo Lee, Sungkyu Jo, Chan Ho Kim, Jong Chul Park, Kyunghwa Yun, Soonock Seol, Ji-Ho Cho, Seungjae Lee, Jin-Yub Lee, Sunghoi Hur
2024 J jnl
Towards Generating Informative Textual Description for Neurons in Language Models.
CoRR
Shrayani Mondal, Rishabh Garodia, Arbaaz Qureshi, Taesung Lee, Youngja Park
2023 — conf
A 3.0 Gb/s/pin 4
VLSI Technology and Circuits
Youngmin Jo, Anil Kavala, Tongsung Kim, Byung-Kwan Chun, Jungjune Park, Taesung Lee, Jungmin Seo, Manjae Yang, Taehyeon Park, Hyunjin Kwon, Cheolhui Lee, Younghoon Son, Junghwan Kwak, Younggyu Lee, Hwan-Seok Ku, Dae-Hoon Na, Changyeon Yu, Jonghoon Park, Jae-Hwan Kim, Hyojin Kwon, Chan-ho Kim, Moon-Ki Jung, Chanjin Park, Donghyun Seo, Moosung Kim, Seungjae Lee, Jin-Yub Lee, Dongku Kang, Chiweon Yoon, Sunghoi Hur
2023 — conf
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of Deep Learning Models.
SP (Workshops)
Nathalie Baracaldo, Farhan Ahmed, Kevin Eykholt, Yi Zhou, Shriti Priya, Taesung Lee, Swanand Kadhe, Mike Tan, Sridevi Polavaram, Sterling Suggs, Yuyang Gao, David Slater
2023 A conf
EdgeTorrent: Real-time Temporal Graph Representations for Intrusion Detection.
RAID
Isaiah J. King, Xiaokui Shu, Jiyong Jang, Kevin Eykholt, Taesung Lee, H. Howie Huang
2023 — conf
Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models.
ACL (1)
Myles Foley, Ambrish Rawat, Taesung Lee, Yufang Hou, Gabriele Picco, Giulio Zizzo
2023 J jnl
Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models.
CoRR
Myles Foley, Ambrish Rawat, Taesung Lee, Yufang Hou, Gabriele Picco, Giulio Zizzo
2023 A* conf
URET: Universal Robustness Evaluation Toolkit (for Evasion).
USENIX Security Symposium
Kevin Eykholt, Taesung Lee, Douglas Lee Schales, Jiyong Jang, Ian M. Molloy, Masha Zorin
2023 J jnl
URET: Universal Robustness Evaluation Toolkit (for Evasion).
CoRR
Kevin Eykholt, Taesung Lee, Douglas Lee Schales, Jiyong Jang, Ian M. Molloy, Masha Zorin
2022 — conf
Advanced novel optical stack technologies for high SNR in CMOS Image Sensor.
VLSI Technology and Circuits
Hye Yeon Park, Yunki Lee, Jonghoon Park, HyunSeok Song, Taesung Lee, Hyung Keun Gweon, Yunji Jung, Jeongmin Bae, Boseong Kim, Junwon Han, Seungwon Kim, Cheolsang Yoon, Jeongki Kim, Changkeun Lee, Sehoon Yoo, Euiyeol Kim, Hyunmin Baek, Howoo Park, Bumsuk Kim, JungChak Ahn, Joonseo Yim
2022 J jnl
Backdoor smoothing: Demystifying backdoor attacks on deep neural networks.
Comput. Secur.
Kathrin Grosse, Taesung Lee, Battista Biggio, Youngja Park, Michael Backes, Ian M. Molloy
2022 — conf
Full-Stack Information Extraction System for Cybersecurity Intelligence.
EMNLP (Industry Track)
Youngja Park, Taesung Lee
2022 J jnl
Robustness of Explanation Methods for NLP Models.
CoRR
Shriya Atmakuri, Tejas Chheda, Dinesh Kandula, Nishant Yadav, Taesung Lee, Hessel Tuinhof
2021 A* conf
Adaptive Verifiable Training Using Pairwise Class Similarity.
AAAI
Shiqi Wang, Kevin Eykholt, Taesung Lee, Jiyong Jang, Ian M. Molloy
2021 — conf
iTurboGraph: Scaling and Automating Incremental Graph Analytics.
SIGMOD Conference
Seongyun Ko, Taesung Lee, Kijae Hong, Wonseok Lee, In Seo, Jiwon Seo, Wook-Shin Han
2020 J jnl
A new measure for overfitting and its implications for backdooring of deep learning.
CoRR
Kathrin Grosse, Taesung Lee, Youngja Park, Michael Backes, Ian M. Molloy
2020 J jnl
Adaptive Verifiable Training Using Pairwise Class Similarity.
CoRR
Shiqi Wang, Kevin Eykholt, Taesung Lee, Jiyong Jang, Ian M. Molloy
2020 — conf
Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries.
ClinicalNLP@EMNLP
Wenjie Wang, Youngja Park, Taesung Lee, Ian M. Molloy, Pengfei Tang, Li Xiong
2019 A* conf
AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos.
ICCV
Chaowei Xiao, Ruizhi Deng, Bo Li, Taesung Lee, Benjamin Edwards, Jinfeng Yi, Dawn Song, Mingyan Liu, Ian M. Molloy
2019 — conf
Defending Against Neural Network Model Stealing Attacks Using Deceptive Perturbations.
IEEE Symposium on Security and Privacy Workshops
Taesung Lee, Benjamin Edwards, Ian M. Molloy, Dong Su
2019 — conf
Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering.
SafeAI@AAAI
Bryant Chen, Wilka Carvalho, Nathalie Baracaldo, Heiko Ludwig, Benjamin Edwards, Taesung Lee, Ian M. Molloy, Biplav Srivastava
2019 — conf
Supervising Unsupervised Open Information Extraction Models.
EMNLP/IJCNLP (1)
Arpita Roy, Youngja Park, Taesung Lee, Shimei Pan
2019 — conf
Unsupervised Sentence Embedding Using Document Structure-Based Context.
ECML/PKDD (2)
Taesung Lee, Youngja Park
2018 J jnl
Defending Against Model Stealing Attacks Using Deceptive Perturbations.
CoRR
Taesung Lee, Benjamin Edwards, Ian M. Molloy, Dong Su
2018 J jnl
Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering.
CoRR
Bryant Chen, Wilka Carvalho, Nathalie Baracaldo, Heiko Ludwig, Benjamin Edwards, Taesung Lee, Ian M. Molloy, Biplav Srivastava
2018 J jnl
List Intersection for Web Search: Algorithms, Cost Models, and Optimizations.
Proc. VLDB Endow.
Sunghwan Kim, Taesung Lee, Seung-won Hwang, Sameh Elnikety
2016 — conf
Linking, integrating, and translating entities via iterative graph matching.
TAAI
Taesung Lee, Seung-won Hwang
2016 B conf
Probabilistic Prototype Model for Serendipitous Property Mining.
COLING
Taesung Lee, Seung-won Hwang, Zhongyuan Wang
2016 B conf
Trivia quiz mining using probabilistic knowledge.
ASONAM
Taesung Lee, Seung-won Hwang, Zhongyuan Wang
2015 J jnl
Processing and Optimizing Main Memory Spatial-Keyword Queries.
Proc. VLDB Endow.
Taesung Lee, Jin-Woo Park, Sanghoon Lee, Seung-won Hwang, Sameh Elnikety, Yuxiong He
2014 A conf
Map Translation Using Geo-tagged Social Media.
EACL
Sunyou Lee, Taesung Lee, Seung-won Hwang
2014 J jnl
Overcoming Asymmetry in Entity Graphs.
IEEE Trans. Knowl. Data Eng.
Taesung Lee, Young-rok Cha, Seung-won Hwang
2014 — conf
Understanding Relation Temporality of Entities.
ACL (2)
Taesung Lee, Seung-won Hwang
2013 A* conf
Attribute extraction and scoring: A probabilistic approach.
ICDE
Taesung Lee, Zhongyuan Wang, Haixun Wang, Seung-won Hwang
2013 — conf
Bootstrapping Entity Translation on Weakly Comparable Corpora.
ACL (1)
Taesung Lee, Seung-won Hwang
2011 J jnl
Web Scale Taxonomy Cleansing.
Proc. VLDB Endow.
Taesung Lee, Zhongyuan Wang, Haixun Wang, Seung-won Hwang