Pseudo Victim AttackER

Pseudo-victim attacker research focuses on understanding and mitigating the effectiveness of various attack strategies against machine learning models and systems. Current research explores diverse attack vectors, including manipulating audio signals (e.g., adding room reverberation to evade deepfake detection), injecting electromagnetic signals into cameras, poisoning training data with backdoors, and exploiting vulnerabilities in physical layer authentication. This work is crucial for improving the robustness and security of AI systems across numerous applications, from cybersecurity and authentication to autonomous systems and IoT devices, by informing the development of more resilient models and defenses.

Papers

November 15, 2024

TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models
Ding Li, Ziqi Zhang, Mengyu Yao, Yifeng Cai, Yao Guo, Xiangqun Chen
Pre Trained Model DNN Model Pseudo Victim AttackER Sensitivity Aware Trusted Execution Environment 3D Graph Test Environment Private Feature Consumer Level GPUs

October 31, 2024

Multi-Robot Pursuit in Parameterized Formation via Imitation Learning
Jinyong Chen, Rui Zhou, Zhaozong Wang, Yunjie Zhang, Guibin Sun
Imitation Learning Formation Control Pseudo Victim AttackER Robot Formation Avoidance Navigation Capture System

October 30, 2024

Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System
Julian Collado, Kevin Stangl
Adversarial Attack Adversarial Perturbation Multiple Model Incomplete Information Pseudo Victim AttackER Proxy Model

September 23, 2024

Room Impulse Responses help attackers to evade Deep Fake Detection
Hieu-Thi Luong, Duc-Tuan Truong, Kong Aik Lee, Eng Siong Chng
Benchmark Study Low Quality Deepfake Room Impulse Response Fake Speech Pseudo Victim AttackER Deep Fake Detection

September 17, 2024

Anti-ESIA: Analyzing and Mitigating Impacts of Electromagnetic Signal Injection Attacks
Denglin Kang, Youqian Zhang, Wai Cheong Tam, Eugene Y. Fu
Camera Model Pseudo Victim AttackER Surveillance Camera Pixel Wise Loss Electromagnetic Signal Injection Attack Impact Reduction

August 21, 2024

Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks
Ziqiang Li, Yueqi Zeng, Pengfei Xia, Lei Liu, Zhangjie Fu, Bin Li
Backdoor Attack Pseudo Victim AttackER Textual Backdoor Attack

August 9, 2024

AttackER: Towards Enhancing Cyber-Attack Attribution with a Named Entity Recognition Dataset
Pritam Deka, Sampath Rajapaksha, Ruby Rani, Amirah Almutairi, Erisa Karafili
Entity Recognition Named Entity Recognition Pseudo Victim AttackER Attack Attribution Threat Attribution

July 11, 2024

AoA-Based Physical Layer Authentication in Analog Arrays under Impersonation Attacks
Muralikrishnan Srinivasan, Linda Senigagliesi, Hui Chen, Arsenia Chorti, Marco Baldi, Henk Wymeersch
Direction of Arrival Estimation Physical Layer Pseudo Victim AttackER Context Impersonation Analog Array

June 4, 2024

Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation
Yaohua Liu, Jiaxin Gao, Xuan Liu, Xianghao Jiao, Xin Fan, Risheng Liu
Adversarial Example Surrogate Model Bilevel Optimization Pseudo Victim AttackER Transfer Attack Sequence Length Reduction

May 2, 2024

Temporal assessment of malicious behaviors: application to turnout field data monitoring
Sara Abdellaoui, Emil Dumitrescu, Cédric Escudero, Eric Zamaï
Application Proficiency High Speed Train System Cyber Attack Real Data Voter Participation Malicious User Pseudo Victim AttackER Real World Attack

April 12, 2024

The Path To Autonomous Cyber Defense
Sean Oesch, Phillipe Austria, Amul Chaulagain, Brian Weber, Cory Watson, Matthew Dixson, Amir Sadovnik
Artificial Intelligence Root to Leaf Path Pseudo Victim AttackER Autonomous Cyber

March 26, 2024

Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning
Joshua C. Zhao, Ahaan Dabholkar, Atul Sharma, Saurabh Bagchi
Private Training Gradient Inversion Data Reconstruction Attack Pseudo Victim AttackER Leakage Attack

March 17, 2024

usfAD Based Effective Unknown Attack Detection Focused IDS Framework
Md. Ashraf Uddin, Sunil Aryal, Mohamed Reda Bouadjenek, Muna Al-Hawawreh, Md. Alamin Talukder
Intrusion Detection Pseudo Victim AttackER Attack Pattern Unknown Attack

January 17, 2024

AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models
Dong shu, Mingyu Jin, Suiyuan Zhu, Beichen Wang, Zihao Zhou, Chong Zhang, Yongfeng Zhang
Jailbreak Attack Robustness Evaluation Pseudo Victim AttackER Attack Efficacy

May 24, 2023

Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model
Aoi Ito, Shota Horiguchi
Self Supervised Learning Anti Spoofing Pseudo Victim AttackER Self Supervised Pre Trained Model Spoofed Speech Pretrained Model

March 28, 2023

A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network
Haodong Zhao, Wei Du, Junjie Guo, Gongshen Liu
Backdoor Attack Speaker Verification Siamese Network Pseudo Victim AttackER Universal Backdoor

February 7, 2023

Catch Me If You Can: Improving Adversaries in Cyber-Security With Q-Learning Algorithms
Arti Bandhana, Ondřej Lukáš, Sebastian Garcia, Tomáš Kroupa
Q Learning Adversary Agent Q Function Pseudo Victim AttackER Cyber Security Double Q Learning

December 29, 2022

"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice
Giovanni Apruzzese, Hyrum S. Anderson, Savino Dambra, David Freeman, Fabio Pierazzi, Kevin A. Roundy
Machine Learning Adversarial Learning Practice Mode Threat Model Gradient Computation Pseudo Victim AttackER Adversarial Machine Learning

December 8, 2022

Simulation of Attacker Defender Interaction in a Noisy Security Game
Erick Galinkin, Emmanouil Pountourakis, John Carter, Spiros Mancoridis
Simulation Study Full Observability Pseudo Victim AttackER Security Game Cybersecurity Environment

November 27, 2022

Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning
Yunchao Zhang, Zonglin Di, Kaiwen Zhou, Cihang Xie, Xin Eric Wang
Local Navigation Federated Prompt Cooperation Vision and Language Navigation Byzantine Robust State of the Art Defense Pseudo Victim AttackER Agent Learning

Pseudo Victim AttackER

Papers

TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models

Multi-Robot Pursuit in Parameterized Formation via Imitation Learning

Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System

Room Impulse Responses help attackers to evade Deep Fake Detection

Anti-ESIA: Analyzing and Mitigating Impacts of Electromagnetic Signal Injection Attacks

Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks

AttackER: Towards Enhancing Cyber-Attack Attribution with a Named Entity Recognition Dataset

AoA-Based Physical Layer Authentication in Analog Arrays under Impersonation Attacks

Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation

Temporal assessment of malicious behaviors: application to turnout field data monitoring

The Path To Autonomous Cyber Defense

Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning

usfAD Based Effective Unknown Attack Detection Focused IDS Framework

AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models

Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model

A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network

Catch Me If You Can: Improving Adversaries in Cyber-Security With Q-Learning Algorithms

"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice

Simulation of Attacker Defender Interaction in a Noisy Security Game

Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning