Targeted Attack

Targeted attacks in machine learning aim to manipulate model inputs or training data to cause specific, undesirable outputs, impacting model reliability and security. Current research focuses on developing increasingly sophisticated attack methods against various models, including deep learning architectures for image recognition, large language models, and time-series forecasting, often employing gradient-based optimization or data manipulation techniques. Understanding and mitigating these attacks is crucial for ensuring the trustworthiness and robustness of machine learning systems across diverse applications, from cybersecurity to healthcare. The field is actively exploring both improved attack strategies and robust defenses.

Papers

October 31, 2024

Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey
Chiyu Zhang, Xiaogang Xu, Jiafei Wu, Zhe Liu, Lu Zhou
Timely Survey Adversarial Attack Vision Task Adversarial Text Last Decade Attack Vector Targeted Attack LLM Attack

August 14, 2024

Boosting Unconstrained Face Recognition with Targeted Style Adversary
Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Seyed Rasoul Hosseini, Nasser M. Nasrabadi
Instance Level Deep Face Recognition Space Augmentation Targeted Attack Unconstrained Face Recognition

January 16, 2024

Revealing Vulnerabilities in Stable Diffusion via Targeted Attacks
Chenyu Zhang, Lanjun Wang, Anan Liu
Adversarial Attack Stable Diffusion Adversarial Prompt Targeted Attack Unveiling Vulnerability

December 4, 2023

InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models
Xunguang Wang, Zhenlan Ji, Pingchuan Ma, Zongjie Li, Shuai Wang
Adversarial Attack Adversarial Example Large Vision Language Model MPT 7b Instruct Targeted Attack

October 23, 2023

On the Detection of Image-Scaling Attacks in Machine Learning
Erwin Quiring, Andreas Müller, Konrad Rieck
Machine Learning Data Detection New Attack Adaptive Adversary Targeted Attack Detection Paradigm Image Scaling

July 12, 2023

Single-Class Target-Specific Attack against Interpretable Deep Learning Systems
Eldor Abdukhamidov, Mohammed Abuhamad, George K. Thiruvathukal, Hyoungshick Kim, Tamer Abuhmed
Adversarial Attack Adversarial Sample Adversarial Loss Interpretable Deep Learning Targeted Attack

April 26, 2023

Improving Adversarial Transferability via Intermediate-level Perturbation Decay
Qizhang Li, Yiwen Guo, Wangmeng Zuo, Hao Chen
Adversarial Example Targeted Attack Adversarial Direction Eigenvalue Decay

April 21, 2023

ANALYSE -- Learning to Attack Cyber-Physical Energy Systems With Intelligent Agents
Thomas Wolgast, Nils Wenninghoff, Stephan Balduin, Eric Veith, Bastian Fraune, Torben Woltjen, Astrid Nieße
Intelligent Agent Cyber Physical Attack Strategy Targeted Attack Energy Market Analyse Text Unknown Attack

March 30, 2023

Mole Recruitment: Poisoning of Image Classifiers via Selective Batch Sampling
Ethan Wisdom, Tejas Gokhale, Chaowei Xiao, Yezhou Yang
Continual LEArning Poisoning Attack Image Classifier Targeted Attack Source Code Vulnerability

February 13, 2023

Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge
Ali Al-Kaswan, Maliheh Izadi, Arie van Deursen
Membership Inference Attack GPT Neo Untargeted Attack Targeted Attack Data Extraction Attack Language Model Training

January 27, 2023

Targeted Attacks on Timeseries Forecasting
Yuvaraj Govindarajulu, Avinash Amballa, Pavan Kulkarni, Manojkumar Parmar
Adversarial Attack Time Series Time Series Forecasting Adversarial Input Targeted Attack Projected Gradient Descent Attack

October 18, 2022

Not All Poisons are Created Equal: Robust Training against Data Poisoning
Yu Yang, Tian Yu Liu, Baharan Mirzasoleiman
Poisoning Attack Data Poisoning Attack Robust Training Data Poisoning State of the Art Defense Targeted Attack Poisoning Efficiency

September 8, 2022

Reward Delay Attacks on Deep Reinforcement Learning
Anindya Sarkar, Jiarui Feng, Yevgeniy Vorobeychik, Christopher Gill, Ning Zhang
Deep Reinforcement Learning Untargeted Attack Novel Attack Targeted Attack Reward Delay

July 16, 2022

MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks
Ali Ramezani-Kebrya, Iman Tabrizian, Fartash Faghri, Petar Popovski
Robust Learning Byzantine Robust Adversarial Agent Aggregated Gradient Byzantine Robust Aggregation Targeted Attack

July 2, 2022

FL-Defender: Combating Targeted Attacks in Federated Learning
Najeeb Jebreel, Josep Domingo-Ferrer
Deep Learning State of the Art Defense Attack Detection Targeted Attack

June 25, 2022

Cascading Failures in Smart Grids under Random, Targeted and Adaptive Attacks
Sushmita Ruj, Arindam Pal
Random Node Smart Grid Random Participation Leg Failure Adaptive Attack Targeted Attack

December 3, 2021

Attack-Centric Approach for Evaluating Transferability of Adversarial Samples in Machine Learning Models
Tochukwu Idika, Ismail Akturk
Machine Learning Machine Learning Model Adversarial Sample Improving Transferability Targeted Attack Attacker Model