|
Poster
|
Wed 2:30
|
Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data
Yujun Zhou · Yufei Han · Haomin Zhuang · Hongyan Bao · Xiangliang Zhang
|
|
|
Poster
|
Tue 2:30
|
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
Zhiyuan Cheng · Zhaoyi Liu · Tengda Guo · Shiwei Feng · Dongfang Liu · Mingjie Tang · Xiangyu Zhang
|
|
|
Poster
|
Thu 4:30
|
DataFreeShield: Defending Adversarial Attacks without Training Data
Hyeyoon Lee · Kanghyun Choi · Dain Kwon · SunJong Park · Mayoore Jaiswal · Noseong Park · Jonghyun Choi · Jinho Lee
|
|
|
Workshop
|
|
Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference
Catherine Huang · Martin Pawelczyk · Himabindu Lakkaraju
|
|
|
Poster
|
Wed 2:30
|
Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
Shuyu Cheng · Yibo Miao · Yinpeng Dong · Xiao Yang · Xiao-Shan Gao · Jun Zhu
|
|
|
Workshop
|
|
Towards Adaptive Attacks on Constrained Tabular Machine Learning
Thibault Simonetto · Salah GHAMIZI · Maxime Cordy
|
|
|
Workshop
|
|
On the Privacy Risks of Post-Hoc Explanations of Foundation Models
Catherine Huang · Martin Pawelczyk · Himabindu Lakkaraju
|
|
|
Workshop
|
|
Attacking Large Language Models with Projected Gradient Descent
Simon Markus Geisler · Tom Wollschläger · M. Hesham Abdalla · Johannes Gasteiger · Stephan Günnemann
|
|
|
Poster
|
Wed 2:30
|
Extending Adversarial Attacks to Produce Adversarial Class Probability Distributions
Jon Vadillo · Roberto Santana · Jose A Lozano
|
|
|
Workshop
|
|
Unified Taxonomy in AI Safety: Watermarks, Adversarial Defenses, and Transferable Attacks
Grzegorz Gluch · Sai Ganesh Nagarajan · Berkant Turan
|
|
|
Poster
|
Tue 2:30
|
RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation
Jiawei Zhou · Linye Lyu · Daojing He · YU LI
|
|
|
Poster
|
Thu 4:30
|
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
Shashank Agnihotri · Steffen Jung · Margret Keuper
|
|
