Untargeted Attack

Untargeted attacks aim to degrade the performance of machine learning models without targeting a specific outcome, posing a significant threat to various applications. Current research focuses on developing and analyzing these attacks across diverse model architectures, including deep reinforcement learning agents, large language models, and hypergraph neural networks, often employing gradient-based methods or data poisoning techniques. Understanding the vulnerabilities exposed by these attacks is crucial for improving the robustness and security of AI systems in domains ranging from cybersecurity and autonomous driving to biometric authentication and federated learning. The development of effective defenses against untargeted attacks is a key area of ongoing investigation.

Papers

November 9, 2024

Target-driven Attack for Large Language Models
Chong Zhang, Mingyu Jin, Dong Shu, Taowen Wang, Dongfang Liu, Xiaobo Jin
Adversarial Text Black Box Attack Untargeted Attack

August 6, 2024

Simple Perturbations Subvert Ethereum Phishing Transactions Detection: An Empirical Analysis
Ahod Alghureid, David Mohaisen
Adversarial Attack Adversarial Training Empirical Analysis Untargeted Attack

July 6, 2024

A Novel Bifurcation Method for Observation Perturbation Attacks on Reinforcement Learning Agents: Load Altering Attacks on a Cyber Physical Power System
Kiernan Broda-Milian, Ranwa Al-Mallah, Hanane Dagdougui
Adversarial Attack Deep Reinforcement Learning Adversarial Example New Attack Reinforcement Learning Agent Renewable Energy Cyber Physical Bifurcation Diagram Untargeted Attack Norm Attack

June 10, 2024

Safety Alignment Should Be Made More Than Just a Few Tokens Deep
Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, Peter Henderson
Fine Tuning Safety Alignment Untargeted Attack Adversarial Suffix

May 24, 2024

BadGD: A unified data-centric framework to identify gradient descent vulnerabilities
Chi-Hua Wang, Guang Cheng
Backdoor Attack Robust Defense Untargeted Attack Adversarial Manipulation Processing Framework

May 2, 2024

Poisoning Attacks on Federated Learning for Autonomous Driving
Sonakshi Garg, Hugo Jönsson, Gustav Kalander, Axel Nilsson, Bhhaanu Pirange, Viktor Valadi, Johan Östman
Autonomous Driving Poisoning Attack Untargeted Attack

February 20, 2024

Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors
Yiwei Lu, Matthew Y. R. Yang, Gautam Kamath, Yaoliang Yu
Transfer Learning Poisoning Attack Data Poisoning Attack Self Supervised Learning Method Pre Trained Feature Extractor Untargeted Attack

February 3, 2024

A Review and Comparison of AI Enhanced Side Channel Analysis
Max Panoff, Honggang Yu, Haoqi Shan, Yier Jin
Consistent Comparison Side Channel Untargeted Attack Hardware Attack

February 1, 2024

Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks
Maan Qraitem, Nazia Tasnim, Piotr Teterwak, Kate Saenko, Bryan A. Plummer
Untargeted Attack Text Attack Typographic Attack

December 20, 2023

PGN: A perturbation generation network against deep reinforcement learning
Xiangjuan Li, Feifan Li, Yang Li, Quan Pan
Generative Model Deep Reinforcement Learning Adversarial Example Untargeted Attack Hidden Representation Perturbation

October 24, 2023

Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networks
Yang Chen, Stjepan Picek, Zhonglin Ye, Zhaoyang Wang, Haixing Zhao
Graph Neural Network Adversarial Attack Hypergraph Neural Network Residual Momentum Untargeted Attack Hypergraph Model

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

April 4, 2023

Untargeted Near-collision Attacks on Biometrics: Real-world Bounds and Theoretical Limits
Axel Durbet, Paul-Marie Grollemund, Kevin Thiry-Atighehchi
Physiological Biometrics General Bound Biometric System Biometric Recognition Fundamental Limit Untargeted Attack Biometric Template

March 29, 2023

Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias
Zihan Liu, Yun Luo, Lirong Wu, Zicheng Liu, Stan Z. Li
Cross Entropy Loss Cross Entropy Untargeted Attack Budget Allocation Graph Poisoning Attack

March 25, 2023

Ensemble-based Blackbox Attacks on Dense Prediction
Zikui Cai, Yaoteng Tan, M. Salman Asif
Adversarial Attack Dense Prediction Untargeted Attack Blackbox Attack

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

December 30, 2022

Guidance Through Surrogate: Towards a Generic Diagnostic Attack
Muzammal Naseer, Salman Khan, Fatih Porikli, Fahad Shahbaz Khan
Adversarial Attack Adversarial DEfense Human Guidance Adversarial Defense Surrogate Assisted Version Untargeted Attack Adversarial Direction Projected Gradient Descent Attack

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

March 31, 2022

Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets
Florian Tramèr, Reza Shokri, Ayrton San Joaquin, Hoang Le, Matthew Jagielski, Sanghyun Hong, Nicholas Carlini
Scientific Inference Membership Inference Attack Privacy Guarantee Inference Attack Untargeted Attack Dark Secret

March 8, 2022

Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection
João Vitorino, Nuno Oliveira, Isabel Praça
Adversarial Attack Adversarial Example Adversarial Training Intrusion Detection Untargeted Attack Realistic Adversarial Perturbation Artifact