Defense Strategy

Defense strategies in machine learning and cybersecurity are actively researched to mitigate vulnerabilities arising from adversarial attacks and inherent model weaknesses. Current efforts focus on developing robust models through techniques like adversarial training, innovative preprocessing, and multi-agent reinforcement learning, alongside exploring diverse defense mechanisms such as watermarking and critical parameter analysis for specific applications like federated learning and network slicing. These advancements are crucial for ensuring the reliability and security of AI systems across various domains, from image classification and natural language processing to critical infrastructure protection. The ultimate goal is to create more trustworthy and resilient systems capable of withstanding sophisticated attacks.

Papers

September 5, 2024

Recent Advances in Attack and Defense Approaches of Large Language Models
Jing Cui, Yishi Xu, Zhewei Huang, Shuchang Zhou, Jianbin Jiao, Junge Zhang
Recent Advance LLM Safety Threat Model Attack Method Attack Vector Defense Strategy

August 20, 2024

Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks
Hetvi Waghela, Jaydip Sen, Sneha Rakshit
Adversarial Attack Adversarial Training Image Classification Adversarial Perturbation Adversarial DEfense Defense Strategy Fast Gradient Sign Method Projected Gradient Descent Attack

July 9, 2024

Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges
Yanli Li, Zhongliang Guo, Nan Yang, Huaming Chen, Dong Yuan, Weiping Ding
Technical Challenge Comprehensive Survey Threat Word Collaborative Machine Learning Defense Strategy Defense Framework

June 25, 2024

Leveraging Reinforcement Learning in Red Teaming for Advanced Ransomware Attack Simulations
Cheng Wang, Christopher Redino, Ryan Clark, Abdul Rahman, Sal Aguinaga, Sathvik Murli, Dhruv Nandakumar, Roland Rao, Lanxiao Huang, Daniel Radke, Edward Bowen
Reinforcement Learning Red Teaming Attack Strategy Attack Method Defense Strategy Ransomware Attack Ransomware Attack Modeling Technique

June 18, 2024

SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation
Xiaoze Liu, Ting Sun, Tianyang Xu, Feijie Wu, Cunxiang Wang, Xiaoqian Wang, Jing Gao
Global Evaluation Text Generation Real Time Defense Strategy Shield Machine Offensive Security

June 6, 2024

Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies
Aswin RRV, Nemika Tyagi, Md Nayem Uddin, Neeraj Varshney, Chitta Baral
Misinformation Claim Kill Chaos Multi Word Keywords Defense Strategy Visual Sycophancy Knowledge Probing

May 29, 2024

New perspectives on the optimal placement of detectors for suicide bombers using metaheuristics
Carlos Cotta, José E. Gallardo
Evolutionary Algorithm Optimization Problem Metaheuristic Algorithm New Perspective State of the Art Detector Adversarial Game Defense Strategy Optimal Placement

January 16, 2024

Investigating Fouling Efficiency in Football Using Expected Booking (xB) Model
Adnan Azmat, Su Su Yi
Full Model Ensemble Method Novel Metric Defense Strategy Football Player

December 21, 2023

Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience
Janvi Thakkar, Giulio Zizzo, Sergio Maffeis
Adversarial Training Agnostic Watermarking Defense Strategy Adversarial Watermarking Model Resilience Copyright Infringement

November 19, 2023

Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies
Feng Wang, M. Cenk Gursoy, Senem Velipasalar
Adversarial Attack Multi Agent Deep Reinforcement Learning Deep RL Network Slicing Multi Agent Policy Defense Strategy

September 28, 2023

Investigating Human-Identifiable Features Hidden in Adversarial Perturbations
Dennis Y. Menn, Tzu-hsun Feng, Sriram Vishwanath, Hung-yi Lee
Adversarial Attack Adversarial Perturbation Untargeted Attack Defense Strategy

August 29, 2023

Can We Rely on AI?
Desmond J. Higham
Artificial Intelligence New Attack Defense Strategy

August 18, 2023

Towards Attack-tolerant Federated Learning via Critical Parameter Analysis
Sungwon Han, Sungwon Park, Fangzhao Wu, Sundong Kim, Bin Zhu, Xing Xie, Meeyoung Cha
Federated Learning Federated Prompt Cooperation Defense Strategy

April 8, 2023

Evolving Reinforcement Learning Environment to Minimize Learner's Achievable Reward: An Application on Hardening Active Directory Systems
Diksha Goel, Aneta Neumann, Frank Neumann, Hung Nguyen, Mingyu Guo
Reinforcement Learning Application Proficiency Attack Graph RL Agent Defense Strategy B Learner Evolutionary Diversity Security Hardening

April 3, 2023

A Multiagent CyberBattleSim for RL Cyber Operation Agents
Thomas Kunz, Christian Fisher, James La Novara-Gsell, Christopher Nguyen, Li Li
Reinforcement Learning RL Agent Defense Strategy Sophisticated Agent Autonomous Reinforcement Learning

January 16, 2023

BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
Siyuan Cheng, Guanhong Tao, Yingqi Liu, Shengwei An, Xiangzhe Xu, Shiwei Feng, Guangyu Shen, Kaiyuan Zhang, Qiuling Xu, Shiqing Ma, Xiangyu Zhang
Backdoor Attack Forensic Analysis Defense Strategy

September 25, 2022

Vision-based Perimeter Defense via Multiview Pose Estimation
Elijah S. Lee, Giuseppe Loianno, Dinesh Jayaraman, Vijay Kumar
Pose Estimation Defense Strategy Perimeter Defense Arriving Intruder

May 27, 2022

Defending Against Stealthy Backdoor Attacks
Sangeet Sagar, Abhinav Bhatt, Abhijith Srinivas Bidaralli
Natural Language Processing Backdoor Attack Stealthy Backdoor Attack Defense Strategy Prior Defense

March 11, 2022

An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacks
Anirudh Yadav, Ashutosh Upadhyay, S. Sharanya
Adversarial Attack Adversarial Sample White Box Auto Encoder Defense Algorithm Automatic Coding Defense Strategy

February 8, 2022

Cyrus 2D Simulation Team Description Paper 2016
Nader Zare, Ashkan Keshavarzi, Seyed Ehsan Beheshtian, Hadi Mowla, Aryan Akbarpour, Hossein Jafari, Keyvan Arab Baraghi, Mohammad Amin Zarifi, Reza Javidan
Practical Algorithm Defense Strategy Soccer Simulation 2 Dimensional Low Complexity Explanation

Defense Strategy

Papers

Recent Advances in Attack and Defense Approaches of Large Language Models

Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks

Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges

Leveraging Reinforcement Learning in Red Teaming for Advanced Ransomware Attack Simulations

SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation

Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies

New perspectives on the optimal placement of detectors for suicide bombers using metaheuristics

Investigating Fouling Efficiency in Football Using Expected Booking (xB) Model

Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience

Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies

Investigating Human-Identifiable Features Hidden in Adversarial Perturbations

Can We Rely on AI?

Towards Attack-tolerant Federated Learning via Critical Parameter Analysis

Evolving Reinforcement Learning Environment to Minimize Learner's Achievable Reward: An Application on Hardening Active Directory Systems

A Multiagent CyberBattleSim for RL Cyber Operation Agents

BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense

Vision-based Perimeter Defense via Multiview Pose Estimation

Defending Against Stealthy Backdoor Attacks

An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacks

Cyrus 2D Simulation Team Description Paper 2016