Adversarial Threat

Adversarial threats target the vulnerabilities of machine learning models by introducing carefully crafted inputs designed to cause misclassification or other undesirable outputs. Current research focuses on understanding and mitigating these threats across various model architectures, including convolutional neural networks (CNNs), large language models (LLMs), and vision-language models (VLMs), employing techniques like adversarial distillation, frequency domain analysis, and diffusion models for defense. This research is crucial for ensuring the reliability and trustworthiness of AI systems in high-stakes applications like autonomous vehicles, healthcare, and cybersecurity, where the consequences of model failure can be severe. The development of robust defenses against adversarial attacks is a critical area of ongoing investigation.

Papers

November 5, 2024

Region-Guided Attack on the Segment Anything Model (SAM)
Xiaoliang Liu, Furao Shen, Jian Zhao
Adversarial Attack Segment Anything Model Adversarial Threat

October 15, 2024

Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks
Kevin Eykholt, Farhan Ahmed, Pratik Vaishnavi, Amir Rahmati
Adversarial Attack Adversarial Learning Camera Lens Critical Review Adversarial Scenario Evasion Attack Adversarial Threat Adversarial Evasion Attack

October 9, 2024

Can DeepFake Speech be Reliably Detected?
Hongbin Liu, Youzheng Chen, Arun Narayanan, Athula Balachandran, Pedro J. Moreno, Lun Wang
Synthesized Speech Voice Cloning Adversarial Threat Synthetic Speech Detector Speech Deepfakes

October 2, 2024

Impact of White-Box Adversarial Attacks on Convolutional Neural Networks
Rakesh Podder, Sudipto Ghosh
Convolutional Neural Network Global Impact Adversarial Threat White Box Adversarial Attack CNN Performance White Box Adversarial

September 23, 2024

Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
Ambrish Rawat, Stefan Schoepf, Giulio Zizzo, Giandomenico Cornacchia, Muhammad Zaid Hameed, Kieran Fraser, Erik Miehling, Beat Buesser, Elizabeth M. Daly, Mark Purcell, Prasanna Sattigeri, Pin-Yu Chen, Kush R. Varshney
Adversarial Attack Technical Challenge Generative AI Visual Perspective Common Pitfall Red Teaming Generative AI System Adversarial Risk Adversarial Threat

September 3, 2024

Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge
Hyejin Park, Dongbo Min
Adversarial Input Adversarial Scenario Adversarial Threat Adversarial Distillation

August 21, 2024

Correlation Analysis of Adversarial Attack in Time Series Classification
Zhengyang Li, Wenhao Liang, Chang Dong, Weitong Chen, Dong Huang
Adversarial Attack Time Series Classification Adversarial Threat Adversarial Manipulation Correlation Analysis

June 13, 2024

MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
Samar Fares, Klea Ziu, Toluwani Aremu, Nikita Durasov, Martin Takáč, Pascal Fua, Karthik Nandakumar, Ivan Laptev
Adversarial Attack Vision Language Model Adversarial Sample Image Domain Adversarial Threat Efficient Adversarial Attack

June 5, 2024

Defending Large Language Models Against Attacks With Residual Stream Activation Analysis
Amelia Kawasaki, Andrew Davis, Houssam Abbas
New Attack Adversarial Input Residual Stream Attack Dataset Adversarial Threat

May 3, 2024

A Novel Approach to Guard from Adversarial Attacks using Stable Diffusion
Trinath Sai Subhash Reddy Pittala, Uma Maheswara Rao Meleti, Geethakrishna Puligundla
Adversarial Attack Adversarial Example Novel Approach Stable Diffusion Robust Defense Safe AI Air Guardian System Adversarial Threat

April 6, 2024

Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
Elita Lobo, Harvineet Singh, Marek Petrik, Cynthia Rudin, Himabindu Lakkaraju
Policy Evaluation Data Poisoning Attack Adversarial Threat

March 25, 2024

The Anatomy of Adversarial Attacks: Concept-based XAI Dissection
Georgii Mikriukov, Gesina Schwalbe, Franz Motzkus, Korinna Bade
Deep Neural Network Adversarial Attack Adversarial Perturbation Interpretable Deep Learning Adversarial Threat XAI Based

March 20, 2024

FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs
Jinmin Li, Kuofeng Gao, Yang Bai, Jingyun Zhang, Shu-tao Xia, Yisen Wang
Large Language Model Adversarial Threat MUltimodal RObustness Consistency Flow Generative Adversarial Network

March 8, 2024

Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume
Ping Guo, Cheng Gong, Xi Lin, Zhiyuan Yang, Qingfu Zhang
Adversarial Attack Native Robustness Adversarial Robustness Adversarial Learning Adversarial Threat

March 5, 2024

Mitigating Label Flipping Attacks in Malicious URL Detectors Using Ensemble Trees
Ehsan Nowroozi, Nada Jadalla, Samaneh Ghelichkhani, Alireza Jolfaei
Backdoor Attack Defense Method Adversarial Threat Label Flipping Attack Url Detection Adversarial Event

January 18, 2024

Vulnerabilities of Foundation Model Integrated Federated Learning Under Adversarial Threats
Chen Wu, Xi Li, Jiaqi Wang
Foundation Model Federated Learning Security Vulnerability Adversarial Threat Federated Learning Client

January 8, 2024

Logits Poisoning Attack in Federated Distillation
Yuhan Tang, Zhiyuan Wu, Bo Gao, Tian Wen, Yuwei Wang, Sheng Sun
Knowledge Distillation Poisoning Attack Federated Distillation Adversarial Threat

September 7, 2023

DiffDefense: Defending against Adversarial Attacks via Diffusion Models
Hondamunige Prasanna Silva, Lorenzo Seidenari, Alberto Del Bimbo
Diffusion Model Adversarial Attack Adversarial DEfense Diffusion Based Method Adversarial Threat

August 9, 2023

SSL-Auth: An Authentication Framework by Fragile Watermarking for Pre-trained Encoders in Self-supervised Learning
Xiaobei Li, Changchun Yin, Liyue Zhu, Xiaogang Xu, Liming Fang, Run Wang, Chenhao Lin
Self Supervised Learning Self Supervised Pre Trained Supervised Learning Adversarial Threat Fragile Watermarking Robust Encoders

February 22, 2023

Mitigating Adversarial Attacks in Deepfake Detection: An Exploration of Perturbation and AI Techniques
Saminder Dhesi, Laura Fontes, Pedro Machado, Isibor Kennedy Ihianle, Farhad Fassihi Tash, David Ada Adama
Deep Learning Adversarial Attack Deep Learning Model Adversarial Example Environment Exploration Deepfake Detection Deep Fake Artificial Intelligence Technique Small Perturbation Adversarial Threat