Wenxiao Wang - RankMe

31 papers A* 10A 1Journal 20

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Can AI-Generated Text be Reliably Detected? Stress Testing AI Text Detectors Under Various Attacks. Trans. Mach. Learn. Res. Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian, Wenxiao Wang, Soheil Feizi
2025	J	`jnl`	Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption. CoRR Wenxiao Wang, Parsa Hosseini, Soheil Feizi
2025	A*	`conf`	DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors. EMNLP Yize Cheng, Wenxiao Wang, Mazda Moayeri, Soheil Feizi
2025	J	`jnl`	DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors. CoRR Yize Cheng, Wenxiao Wang, Mazda Moayeri, Soheil Feizi
2025	J	`jnl`	Gaming Tool Preferences in Agentic LLMs. CoRR Kazem Faghih, Wenxiao Wang, Yize Cheng, Siddhant Bharti, Gaurang Sriramanan, Sriram Balasubramanian, Parsa Hosseini, Soheil Feizi
2025	J	`jnl`	Maestro: Joint Graph & Config Optimization for Reliable AI Agents. CoRR Wenxiao Wang, Priyatham Kattakinda, Soheil Feizi
2025	J	`jnl`	Temporal Blindness in Multi-Turn LLM Agents: Misaligned Tool Use vs. Human Time Perception. CoRR Yize Cheng, Arshia Soltani Moakhar, Chenrui Fan, Kazem Faghih, Parsa Hosseini, Wenxiao Wang, Soheil Feizi
2025	A*	`conf`	Tool Preferences in Agentic LLMs are Unreliable. EMNLP Kazem Faghih, Wenxiao Wang, Yize Cheng, Siddhant Bharti, Gaurang Sriramanan, Sriram Balasubramanian, Parsa Hosseini, Soheil Feizi
2024	A*	`conf`	DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness. ICLR Shoumik Saha, Wenxiao Wang, Yigitcan Kaya, Soheil Feizi, Tudor Dumitras
2024	A*	`conf`	Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks. ICLR Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei, Aounon Kumar, Atoosa Malemir Chegini, Wenxiao Wang, Soheil Feizi
2024	J	`jnl`	Towards Fundamentally Scalable Model Selection: Asymptotically Fast Update and Selection. CoRR Wenxiao Wang, Weiming Zhuang, Lingjuan Lyu
2023	J	`jnl`	Adversarial Robustness of Learning-based Static Malware Classifiers. CoRR Shoumik Saha, Wenxiao Wang, Yigitcan Kaya, Soheil Feizi
2023	J	`jnl`	Can AI-Generated Text be Reliably Detected? CoRR Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian, Wenxiao Wang, Soheil Feizi
2023	J	`jnl`	On Practical Aspects of Aggregation Defenses against Data Poisoning Attacks. CoRR Wenxiao Wang, Soheil Feizi
2023	J	`jnl`	Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks. CoRR Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei, Aounon Kumar, Atoosa Malemir Chegini, Wenxiao Wang, Soheil Feizi
2023	A*	`conf`	Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases. NeurIPS Mazda Moayeri, Wenxiao Wang, Sahil Singla, Soheil Feizi
2023	J	`jnl`	Temporal Robustness against Data Poisoning. CoRR Wenxiao Wang, Soheil Feizi
2023	A*	`conf`	Temporal Robustness against Data poisoning. NeurIPS Wenxiao Wang, Soheil Feizi
2022	A*	`conf`	Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation. ICML Wenxiao Wang, Alexander Levine, Soheil Feizi
2022	J	`jnl`	Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation. CoRR Wenxiao Wang, Alexander Levine, Soheil Feizi
2022	A*	`conf`	Lethal Dose Conjecture on Data Poisoning. NeurIPS Wenxiao Wang, Alexander Levine, Soheil Feizi
2022	J	`jnl`	Lethal Dose Conjecture on Data Poisoning. CoRR Wenxiao Wang, Alexander Levine, Soheil Feizi
2022	J	`jnl`	Spuriosity Rankings: Sorting Data for Spurious Correlation Robustness. CoRR Mazda Moayeri, Wenxiao Wang, Sahil Singla, Soheil Feizi
2021	J	`jnl`	DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing. CoRR Wenxiao Wang, Tianhao Wang, Lun Wang, Nanqing Luo, Pan Zhou, Dawn Song, Ruoxi Jia
2021	J	`jnl`	DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing. Proc. Priv. Enhancing Technol. Wenxiao Wang, Tianhao Wang, Lun Wang, Nanqing Luo, Pan Zhou, Dawn Song, Ruoxi Jia
2021	A*	`conf`	On Feature Decorrelation in Self-Supervised Learning. ICCV Tianyu Hua, Wenxiao Wang, Zihui Xue, Sucheng Ren, Yue Wang, Hang Zhao
2021	J	`jnl`	On Feature Decorrelation in Self-Supervised Learning. CoRR Tianyu Hua, Wenxiao Wang, Zihui Xue, Yue Wang, Sucheng Ren, Hang Zhao
2021	A	`conf`	REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data. AsiaCCS Xinyun Chen, Wenxiao Wang, Chris Bender, Yiming Ding, Ruoxi Jia, Bo Li, Dawn Song
2020	A*	`conf`	The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks. CVPR Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, Dawn Song
2019	J	`jnl`	REFIT: a Unified Watermark Removal Framework for Deep Learning Systems with Limited Data. CoRR Xinyun Chen, Wenxiao Wang, Chris Bender, Yiming Ding, Ruoxi Jia, Bo Li, Dawn Song
2019	J	`jnl`	The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks. CoRR Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, Dawn Song