Adversarial Attacks are Reversible with Natural Supervision

26 March 2021

Carl Vondrick

Papers citing "Adversarial Attacks are Reversible with Natural Supervision"

20 / 20 papers shown

Title
SPIN: Self-Supervised Prompt INjection Leon Zhou Junfeng Yang Chengzhi Mao AAML SILM 30 0 0 17 Oct 2024
Secure Video Quality Assessment Resisting Adversarial Attacks Ao Zhang Yu Ran Weixuan Tang Yuan-Gen Wang Qingxiao Guan Chunsheng Yang AAML 34 0 0 09 Oct 2024
Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character Siyuan Ma Weidi Luo Yu Wang Xiaogeng Liu 38 20 0 25 May 2024
Robustifying Language Models with Test-Time Adaptation Noah T. McDermott Junfeng Yang Chengzhi Mao 21 2 0 29 Oct 2023
How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses Joana Cabral Costa Tiago Roxo Hugo Manuel Proença Pedro R. M. Inácio AAML 40 50 0 18 May 2023
Convolutional Visual Prompt for Robust Visual Perception Yun-Yun Tsai Chengzhi Mao Junfeng Yang VLM VPVLM 31 13 0 01 Mar 2023
Beckman Defense A. V. Subramanyam OOD AAML 40 0 0 04 Jan 2023
Understanding Zero-Shot Adversarial Robustness for Large-Scale Models Chengzhi Mao Scott Geng Junfeng Yang Xin Eric Wang Carl Vondrick VLM 44 59 0 14 Dec 2022
Adversarially Robust Video Perception by Seeing Motion Lingyu Zhang Chengzhi Mao Junfeng Yang Carl Vondrick VGen AAML 44 2 0 13 Dec 2022
Robust Perception through Equivariance Chengzhi Mao Lingyu Zhang Abhishek Joshi Junfeng Yang Hongya Wang Carl Vondrick BDL AAML 29 7 0 12 Dec 2022
Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses A. Kolli M. Jehanzeb Mirza Horst Possegger Horst Bischof AAML 32 1 0 10 Nov 2022
Adversarial Purification with the Manifold Hypothesis Zhaoyuan Yang Zhiwei Xu Jing Zhang Richard I. Hartley Peter Tu AAML 24 5 0 26 Oct 2022
Visual Prompting for Adversarial Robustness Aochuan Chen P. Lorenz Yuguang Yao Pin-Yu Chen Sijia Liu VLM VPVLM 38 32 0 12 Oct 2022
Landscape Learning for Neural Network Inversion Ruoshi Liu Chen-Guang Mao Purva Tendulkar Hongya Wang Carl Vondrick 35 8 0 17 Jun 2022
Using Multiple Self-Supervised Tasks Improves Model Robustness Matthew Lawhon Chengzhi Mao Junfeng Yang AAML SSL 14 4 0 07 Apr 2022
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses Francesco Croce Sven Gowal T. Brunner Evan Shelhamer Matthias Hein A. Cemgil TTA AAML 181 67 0 28 Feb 2022
MEMO: Test Time Robustness via Adaptation and Augmentation Marvin Zhang Sergey Levine Chelsea Finn OOD TTA 40 303 0 18 Oct 2021
Improved Baselines with Momentum Contrastive Learning Xinlei Chen Haoqi Fan Ross B. Girshick Kaiming He SSL 270 3,375 0 09 Mar 2020
A New Defense Against Adversarial Images: Turning a Weakness into a Strength Tao Yu Shengyuan Hu Chuan Guo Wei-Lun Chao Kilian Q. Weinberger AAML 58 101 0 16 Oct 2019
Adversarial examples in the physical world Alexey Kurakin Ian Goodfellow Samy Bengio SILM AAML 287 5,837 0 08 Jul 2016