Illusory Attacks: Information-Theoretic Detectability Matters in
Adversarial Attacks

Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks

20 July 2022

Stephen McAleer

João F. Henriques

Jakob N. Foerster

Christian Schroeder de Witt

Papers citing "Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks"

8 / 8 papers shown

Title
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents Christian Schroeder de Witt AAML AI4CE 150 1 0 04 May 2025
Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits Andis Draguns Andrew Gritsevskiy S. Motwani Charlie Rogers-Smith Jeffrey Ladish Christian Schroeder de Witt 40 2 0 03 Jun 2024
Balancing detectability and performance of attacks on the control channel of Markov Decision Processes Alessio Russo Alexandre Proutière AAML 35 6 0 15 Sep 2021
Robust Reinforcement Learning on State Observations with Learned Optimal Adversary Huan Zhang Hongge Chen Duane S. Boning Cho-Jui Hsieh 67 162 0 21 Jan 2021
Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles Ranjie Duan Xingjun Ma Yisen Wang James Bailey •. A. K. Qin Yun Yang AAML 167 224 0 08 Mar 2020
Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning Inaam Ilahi Muhammad Usama Junaid Qadir M. Janjua Ala I. Al-Fuqaha D. Hoang Dusit Niyato AAML 59 132 0 27 Jan 2020
ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector Shang-Tse Chen Cory Cornelius Jason Martin Duen Horng Chau ObjD 153 424 0 16 Apr 2018
Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression Nilaksh Das Madhuri Shanbhogue Shang-Tse Chen Fred Hohman Siwei Li Li-Wei Chen Michael E. Kounavis Duen Horng Chau FedML AAML 43 224 0 19 Feb 2018