Successful Adversarial Attack

Successful adversarial attacks exploit vulnerabilities in machine learning models by subtly altering inputs to cause misclassifications or undesired outputs. Current research focuses on developing more effective attack methods, particularly those that generate diverse and novel attacks across various model types, including large language models and image segmentation networks, often employing techniques like gradient-based optimization and reinforcement learning. Understanding and mitigating these attacks is crucial for ensuring the reliability and safety of AI systems across diverse applications, from autonomous vehicles to medical image analysis and online content moderation.

Papers

June 26, 2024

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
Liwei Jiang, Kavel Rao, Seungju Han, Allyson Ettinger, Faeze Brahman, Sachin Kumar, Niloofar Mireshghallah, Ximing Lu, Maarten Sap, Yejin Choi, Nouha Dziri
Language Model Visual Analogue Scale Jailbreak Attack Synthetic Dataset Red Teaming Successful Adversarial Attack Human Team Jailbreak Evaluation

June 24, 2024

Automated Adversarial Discovery for Safety Classifiers
Yash Kumar Lal, Preethi Lahoti, Aradhana Sinha, Yao Qin, Ananth Balashankar
Adversarial Attack Successful Adversarial Attack Safety Classifier

January 20, 2024

Susceptibility of Adversarial Attack on Medical Image Segmentation Models
Zhongxuan Wang, Leo Xu
Adversarial Attack Successful Adversarial Attack Medical Image Segmentation Model

November 14, 2023

Physical Adversarial Examples for Multi-Camera Systems
Ana Răduţoiu, Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger
Adversarial Example Multi Camera Multiple Camera Physical Adversarial Successful Adversarial Attack

August 29, 2023

Advancing Adversarial Robustness Through Adversarial Logit Update
Hao Xuan, Peican Zhu, Xingyu Li
Adversarial Attack Adversarial Training Adversarial Robustness Adversarial Sample Adversarial Purification Successful Adversarial Attack

May 18, 2023

Deep PackGen: A Deep Reinforcement Learning Framework for Adversarial Network Packet Generation
Soumyadeep Hore, Jalal Ghadermazi, Diwas Paudel, Ankit Shah, Tapas K. Das, Nathaniel D. Bastian
Adversarial Attack Network Intrusion Detection Evasion Attack Adversarial Generation Successful Adversarial Attack

March 24, 2023

How many dimensions are required to find an adversarial example?
Charles Godfrey, Henry Kvinge, Elise Bishoff, Myles Mckay, Davis Brown, Tim Doster, Eleanor Byler
Adversarial Example Adversarial Vulnerability High Dimensional Space Successful Adversarial Attack Higher Dimension

July 4, 2022

RAF: Recursive Adversarial Attacks on Face Recognition Using Extremely Limited Queries
Keshav Kasichainula, Hadi Mansourifar, Weidong Shi
Adversarial Attack Adversarial Example Face Recognition Successful Adversarial Attack

June 28, 2022

Collecting high-quality adversarial data for machine reading comprehension tasks with humans and models in the loop
Damian Y. Romero Diaz, Magdalena Anioł, John Culnan
Full Model Real Human High Quality Machine Reading Comprehension Adversarial Data Adversarial Data Collection Extractive Question Annotation Study Successful Adversarial Attack

June 24, 2022

Robustness of Explanation Methods for NLP Models
Shriya Atmakuri, Tejas Chheda, Dinesh Kandula, Nishant Yadav, Taesung Lee, Hessel Tuinhof
Native Robustness Adversarial Robustness Text Modality NLP Model Explanation Method Textual Explanation Successful Adversarial Attack

March 2, 2022

Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers
Evan Crothers, Nathalie Japkowicz, Herna Viktor, Paula Branco
Adversarial Attack Data Detection Adversarial Robustness Generated Text Generative Transformer Deep Learning Feature Successful Adversarial Attack

January 29, 2022

Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses
Mengting Xu, Tao Zhang, Zhongnian Li, Daoqiang Zhang
Adversarial DEfense Adversarial Defense Successful Adversarial Attack Projected Gradient Descent Attack

November 22, 2021

Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
Utku Ozbulak, Maura Pintor, Arnout Van Messem, Wesley De Neve
Adversarial Attack Adversarial Example Supervised ImageNet Adversarial Learning Reality Check Successful Adversarial Attack ImageNet Hierarchy

Successful Adversarial Attack

Papers

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

Automated Adversarial Discovery for Safety Classifiers

Susceptibility of Adversarial Attack on Medical Image Segmentation Models

Physical Adversarial Examples for Multi-Camera Systems

Advancing Adversarial Robustness Through Adversarial Logit Update

Deep PackGen: A Deep Reinforcement Learning Framework for Adversarial Network Packet Generation

How many dimensions are required to find an adversarial example?

RAF: Recursive Adversarial Attacks on Face Recognition Using Extremely Limited Queries

Collecting high-quality adversarial data for machine reading comprehension tasks with humans and models in the loop

Robustness of Explanation Methods for NLP Models

Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers

Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes