Adversarial Search

Adversarial search explores methods for finding inputs that intentionally mislead machine learning models, revealing vulnerabilities and improving robustness. Current research focuses on developing efficient attack algorithms, such as beam search methods, and robust defenses, including techniques leveraging uncertainty estimation and classical machine learning models for verification. This field is crucial for enhancing the security and reliability of AI systems across diverse applications, from image recognition and natural language processing to autonomous systems and search engines. The development of both effective attacks and defenses is driving improvements in model design and evaluation methodologies.

Papers

July 14, 2024

Augmented Neural Fine-Tuning for Efficient Backdoor Purification
Nazmul Karim, Abdullah Al Arafat, Umar Khalid, Zhishan Guo, Nazanin Rahnavard
Fine Tuning Backdoor Attack Adversarial Search Backdoor Purification

June 26, 2024

Adversarial Search Engine Optimization for Large Language Models
Fredrik Nestaas, Edoardo Debenedetti, Florian Tramèr
Adversarial Search Preference Poisoning

February 23, 2024

Fast Adversarial Attacks on Language Models In One GPU Minute
Vinu Sankar Sadasivan, Shoumik Saha, Gaurang Sriramanan, Priyatham Kattakinda, Atoosa Chegini, Soheil Feizi
Language Model Membership Inference Attack Adversarial Prompt Attack Success Rate Adversarial Search

January 21, 2024

Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion
Aly M. Kassem, Sherif Saad
Adversarial Attack Adversarial Example Adversarial Sample Needle Insertion Public Exception Adversarial Search

October 17, 2023

Stealthy Terrain-Aware Multi-Agent Active Search
Nikhil Angad Bakshi, Jeff Schneider
Terrain Aware Adversarial Search Multi Agent Active Search

June 20, 2023

Adversarial Search and Tracking with Multiagent Reinforcement Learning in Sparsely Observable Environment
Zixuan Wu, Sean Ye, Manisha Natarajan, Letian Chen, Rohan Paleja, Matthew C. Gombolay
Reinforcement Learning Web Tracking Observable Environment Conflict Detection Adversarial Search Sparse Text

June 16, 2023

CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search
Fahad Shamshad, Muzammal Naseer, Karthik Nandakumar
Privacy Protection Makeup Transfer Adversarial Code Adversarial Search

June 1, 2023

December 20, 2022

AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning
Aowabin Rahman, Arnab Bhattacharya, Thiagarajan Ramachandran, Sayak Mukherjee, Himanshu Sharma, Ted Fujimoto, Samrat Chatterjee
Multi Agent Reinforcement Learning Search and Rescue Multi Robot Team Monotone Adversary Adversarial Search Adversarial Multi Adversarial Communication

October 22, 2022

ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation
Fan Yin, Yao Li, Cho-Jui Hsieh, Kai-Wei Chang
Adversarial Attack Adversarial Example Data Detection Raw Data Model Uncertainty Adversarial Search

Adversarial Search

Papers

Augmented Neural Fine-Tuning for Efficient Backdoor Purification

Adversarial Search Engine Optimization for Large Language Models

Fast Adversarial Attacks on Language Models In One GPU Minute

Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion

Stealthy Terrain-Aware Multi-Agent Active Search

Adversarial Search and Tracking with Multiagent Reinforcement Learning in Sparsely Observable Environment

CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search

Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search

Adversarial-Aware Deep Learning System based on a Secondary Classical Machine Learning Verification Approach

AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning

ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation