Chawin Sitawarin

51 papers A* 11Misc 1Journal 28Unranked 10

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	Defending Against Prompt Injection With a Few DefensiveTokens. AISec@CCS Sizhe Chen, Yizhu Wang, Nicholas Carlini, Chawin Sitawarin, David A. Wagner
2025	J	`jnl`	Defending Against Prompt Injection With a Few DefensiveTokens. CoRR Sizhe Chen, Yizhu Wang, Nicholas Carlini, Chawin Sitawarin, David A. Wagner
2025	J	`jnl`	Does More Inference-Time Compute Really Help Robustness? CoRR Tong Wu, Chong Xiang, Jiachen T. Wang, Weichen Yu, Chawin Sitawarin, Vikash Sehwag, Prateek Mittal
2025	J	`jnl`	Extracting alignment data in open models. CoRR Federico Barbero, Xiangming Gu, Christopher A. Choquette-Choo, Chawin Sitawarin, Matthew Jagielski, Itay Yona, Petar Velickovic, Ilia Shumailov, Jamie Hayes
2025	J	`jnl`	How much do language models memorize? CoRR John X. Morris, Chawin Sitawarin, Chuan Guo, Narine Kokhlikyan, G. Edward Suh, Alexander M. Rush, Kamalika Chaudhuri, Saeed Mahloujifar
2025	—	`conf`	JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift. AISec@CCS Julien Piet, Xiao Huang, Dennis Jacob, Annabella Chow, Maha Alrashed, Geng Zhao, Zhanhao Hu, Chawin Sitawarin, Basel Alomair, David A. Wagner
2025	J	`jnl`	JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift. CoRR Julien Piet, Xiao Huang, Dennis Jacob, Annabella Chow, Maha Alrashed, Geng Zhao, Zhanhao Hu, Chawin Sitawarin, Basel Alomair, David A. Wagner
2025	J	`jnl`	Lessons from Defending Gemini Against Indirect Prompt Injections. CoRR Chongyang Shi, Sharon Lin, Shuang Song, Jamie Hayes, Ilia Shumailov, Itay Yona, Juliette Pluto, Aneesh Pappu, Christopher A. Choquette-Choo, Milad Nasr, Chawin Sitawarin, Gena Gibson, Andreas Terzis, John Flynn
2025	—	`conf`	MARKMyWORDS: Analyzing and Evaluating Language Model Watermarks. SaTML Julien Piet, Chawin Sitawarin, Vivian Fang, Norman Mu, David A. Wagner
2025	J	`jnl`	Soft Instruction De-escalation Defense. CoRR Nils Philipp Walter, Chawin Sitawarin, Jamie Hayes, David Stutz, Ilia Shumailov
2025	—	`conf`	Stronger Universal and Transferable Attacks by Suppressing Refusals. NAACL (Long Papers) David Huang, Avidan Shah, Alexandre Araujo, David A. Wagner, Chawin Sitawarin
2025	A*	`conf`	StruQ: Defending Against Prompt Injection with Structured Queries. USENIX Security Symposium Sizhe Chen, Julien Piet, Chawin Sitawarin, David A. Wagner
2025	J	`jnl`	The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections. CoRR Milad Nasr, Nicholas Carlini, Chawin Sitawarin, Sander V. Schulhoff, Jamie Hayes, Michael Ilie, Juliette Pluto, Shuang Song, Harsh Chaudhari, Ilia Shumailov, Abhradeep Thakurta, Kai Yuanqing Xiao, Andreas Terzis, Florian Tramèr
2025	A*	`conf`	Vulnerability Detection with Code Language Models: How Far are We? ICSE Yangruibo Ding, Yanjun Fu, Omniyyah Ibrahim, Chawin Sitawarin, Xinyun Chen, Basel Alomair, David A. Wagner, Baishakhi Ray, Yizheng Chen
2024	—	`conf`	Jatmo: Prompt Injection Defense by Task-Specific Finetuning. ESORICS (1) Julien Piet, Maha Alrashed, Chawin Sitawarin, Sizhe Chen, Zeming Wei, Elizabeth Sun, Basel Alomair, David A. Wagner
2024	—	`—`	New Perspectives on Adversarially Robust Machine Learning Systems Chawin Sitawarin
2024	A*	`conf`	OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift. ICML Lin Li, Yifei Wang, Chawin Sitawarin, Michael W. Spratling
2024	J	`jnl`	PAL: Proxy-Guided Black-Box Attack on Large Language Models. CoRR Chawin Sitawarin, Norman Mu, David A. Wagner, Alexandre Araujo
2024	A*	`conf`	PubDef: Defending Against Transfer Attacks From Public Models. ICLR Chawin Sitawarin, Jaewon Chang, David Huang, Wesson Altoyan, David A. Wagner
2024	A*	`conf`	SPDER: Semiperiodic Damping-Enabled Object Representation. ICLR Kathan Shah, Chawin Sitawarin
2024	J	`jnl`	StruQ: Defending Against Prompt Injection with Structured Queries. CoRR Sizhe Chen, Julien Piet, Chawin Sitawarin, David A. Wagner
2024	J	`jnl`	Vulnerability Detection with Code Language Models: How Far Are We? CoRR Yangruibo Ding, Yanjun Fu, Omniyyah Ibrahim, Chawin Sitawarin, Xinyun Chen, Basel Alomair, David A. Wagner, Baishakhi Ray, Yizheng Chen
2023	J	`jnl`	Defending Against Transfer Attacks From Public Models. CoRR Chawin Sitawarin, Jaewon Chang, David Huang, Wesson Altoyan, David A. Wagner
2023	J	`jnl`	Jatmo: Prompt Injection Defense by Task-Specific Finetuning. CoRR Julien Piet, Maha Alrashed, Chawin Sitawarin, Sizhe Chen, Zeming Wei, Elizabeth Sun, Basel Alomair, David A. Wagner
2023	J	`jnl`	Mark My Words: Analyzing and Evaluating Language Model Watermarks. CoRR Julien Piet, Chawin Sitawarin, Vivian Fang, Norman Mu, David A. Wagner
2023	J	`jnl`	OODRobustBench: benchmarking and analyzing adversarial robustness under distribution shift. CoRR Lin Li, Yifei Wang, Chawin Sitawarin, Michael W. Spratling
2023	A*	`conf`	Part-Based Models Improve Adversarial Robustness. ICLR Chawin Sitawarin, Kornrapat Pongmala, Yizheng Chen, Nicholas Carlini, David A. Wagner
2023	A*	`conf`	Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems. ICML Chawin Sitawarin, Florian Tramèr, Nicholas Carlini
2023	A*	`conf`	REAP: A Large-Scale Realistic Adversarial Patch Benchmark. ICCV Nabeel Hingun, Chawin Sitawarin, Jerry Li, David A. Wagner
2023	J	`jnl`	SPDER: Semiperiodic Damping-Enabled Object Representation. CoRR Kathan Shah, Chawin Sitawarin
2023	—	`conf`	Short: Certifiably Robust Perception Against Adversarial Patch Attacks: A Survey. VehicleSec Chong Xiang, Chawin Sitawarin, Tong Wu, Prateek Mittal
2022	A*	`conf`	Demystifying the Adversarial Robustness of Random Transformation Defenses. ICML Chawin Sitawarin, Zachary J. Golan-Strieb, David A. Wagner
2022	J	`jnl`	Demystifying the Adversarial Robustness of Random Transformation Defenses. CoRR Chawin Sitawarin, Zachary J. Golan-Strieb, David A. Wagner
2022	J	`jnl`	Part-Based Models Improve Adversarial Robustness. CoRR Chawin Sitawarin, Kornrapat Pongmala, Yizheng Chen, Nicholas Carlini, David A. Wagner
2022	J	`jnl`	Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems. CoRR Chawin Sitawarin, Florian Tramèr, Nicholas Carlini
2022	J	`jnl`	REAP: A Large-Scale Realistic Adversarial Patch Benchmark. CoRR Nabeel Hingun, Chawin Sitawarin, Jerry Li, David A. Wagner
2021	A*	`conf`	Adversarial Examples for k-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams. NeurIPS Chawin Sitawarin, Evgenios M. Kornaropoulos, Dawn Song, David A. Wagner
2021	—	`conf`	SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothing. AISec@CCS Chawin Sitawarin, Supriyo Chakraborty, David A. Wagner
2020	J	`jnl`	Adversarial Examples for k-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams. CoRR Chawin Sitawarin, Evgenios M. Kornaropoulos, Dawn Song, David A. Wagner
2020	J	`jnl`	Improving Adversarial Robustness Through Progressive Hardening. CoRR Chawin Sitawarin, Supriyo Chakraborty, David A. Wagner
2020	—	`conf`	Minimum-Norm Adversarial Examples on KNN and KNN based Models. SP (Workshops) Chawin Sitawarin, David A. Wagner
2020	J	`jnl`	Minimum-Norm Adversarial Examples on KNN and KNN-Based Models. CoRR Chawin Sitawarin, David A. Wagner
2019	—	`conf`	Analyzing the Robustness of Open-World Machine Learning. AISec@CCS Vikash Sehwag, Arjun Nitin Bhagoji, Liwei Song, Chawin Sitawarin, Daniel Cullina, Mung Chiang, Prateek Mittal
2019	J	`jnl`	Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples. CoRR Vikash Sehwag, Arjun Nitin Bhagoji, Liwei Song, Chawin Sitawarin, Daniel Cullina, Mung Chiang, Prateek Mittal
2019	—	`conf`	On the Robustness of Deep K-Nearest Neighbors. IEEE Symposium on Security and Privacy Workshops Chawin Sitawarin, David A. Wagner
2019	J	`jnl`	On the Robustness of Deep K-Nearest Neighbors. CoRR Chawin Sitawarin, David A. Wagner
2018	J	`jnl`	DARTS: Deceiving Autonomous Cars with Toxic Signs. CoRR Chawin Sitawarin, Arjun Nitin Bhagoji, Arsalan Mosenia, Mung Chiang, Prateek Mittal
2018	Misc	`conf`	Enhancing robustness of machine learning systems via data transformations. CISS Arjun Nitin Bhagoji, Daniel Cullina, Chawin Sitawarin, Prateek Mittal
2018	A*	`conf`	Not All Pixels are Born Equal: An Analysis of Evasion Attacks under Locality Constraints. CCS Vikash Sehwag, Chawin Sitawarin, Arjun Nitin Bhagoji, Arsalan Mosenia, Mung Chiang, Prateek Mittal
2018	J	`jnl`	Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logos. CoRR Chawin Sitawarin, Arjun Nitin Bhagoji, Arsalan Mosenia, Prateek Mittal, Mung Chiang
2017	J	`jnl`	Beyond Grand Theft Auto V for Training, Testing and Enhancing Deep Learning in Self Driving Cars. CoRR Mark Martinez, Chawin Sitawarin, Kevin Finch, Lennart Meincke, Alex Yablonski, Alain L. Kornhauser