firstbacksecondback
28 Results
|
Affinity Event
|
MLSherlock: An Audit Lens for Policy-Compliance Machine Learning Systems Ismat Jarin · Tu Le · Athina Markopoulou |
||
|
Poster
|
Thu 11:00 |
Intrinsic Self-Supervision for Data Quality Audits Fabian Gröger · Simone Lionetti · Philippe Gottfrois · Alvaro Gonzalez-Jimenez · Ludovic Amruthalingam · Matthew Groh · Alexander Navarini · Marc Pouly |
|
|
Affinity Event
|
Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset Khaoula Chehbouni · Jonathan Colaço Carr · Yash More · Jackie CK Cheung · Golnoosh Farnadi |
||
|
Poster
|
Thu 11:00 |
Statistical Inference for Fairness Auditing John Cherian · Emmanuel Candes |
|
|
Poster
|
Thu 16:30 |
Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets Ike Obi · Rohan Pant · Srishti Shekhar Agrawal · Maham Ghazanfar · Aaron Basiletti |
|
|
Poster
|
Wed 11:00 |
FinBen: A Holistic Financial Benchmark for Large Language Models Qianqian Xie · Weiguang Han · Zhengyu Chen · Ruoyu Xiang · Xiao Zhang · Yueru He · Mengxi Xiao · Dong Li · Yongfu Dai · Duanyu Feng · Yijing Xu · Haoqiang Kang · Ziyan Kuang · Chenhan Yuan · Kailai Yang · Zheheng Luo · Tianlin Zhang · Zhiwei Liu · GUOJUN XIONG · Zhiyang Deng · Yuechen Jiang · Zhiyuan Yao · Haohang Li · Yangyang Yu · Gang Hu · Huang Jiajia · Xiaoyang Liu · Alejandro Lopez-Lira · Benyou Wang · Yanzhao Lai · Hao Wang · Min Peng · Sophia Ananiadou · Jimin Huang |
|
|
Poster
|
Fri 16:30 |
Auditing Privacy Mechanisms via Label Inference Attacks Róbert Busa-Fekete · Travis Dick · Claudio Gentile · Andres Munoz Medina · Adam Smith · Marika Swanberg |
|
|
Poster
|
Fri 11:00 |
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining Mishaal Kazmi · Hadrien Lautraite · Alireza Akbari · Qiaoyue Tang · Mauricio Soroco · Tao Wang · Sébastien Gambs · Mathias Lécuyer |
|
|
Poster
|
Fri 11:00 |
Auditing Local Explanations is Hard Robi Bhattacharjee · Ulrike Luxburg |
|
|
Poster
|
Wed 16:30 |
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning Meenatchi Sundaram Muthu Selva Annamalai · Emiliano De Cristofaro |
|
|
Workshop
|
Sat 12:00 |
Optimizing Adversarial Samples for Tighter Privacy Auditing in Final Model-Only Settings Sangyeon Yoon · Wonje Jeung · Albert No |
|
|
Affinity Event
|
Gender Trouble in Word Embeddings: A Critical Audit of BERT Guided by Gender Performativity Theory Franziska Sofia Hafner |