Malicious Sample

Malicious samples, encompassing malware, adversarial examples, and backdoored models, pose significant threats to the security and reliability of machine learning systems. Current research focuses on detecting and mitigating these threats through various techniques, including novel dataset creation for improved model training, the development of robust detection algorithms (e.g., those leveraging graph contrastive learning or parameter-oriented scaling consistency), and the design of defenses against attacks targeting test-time adaptation or federated learning. Understanding and addressing these vulnerabilities is crucial for ensuring the trustworthiness and safety of AI systems across diverse applications, from cybersecurity to healthcare.

Papers

September 29, 2024

T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
Chen Yeh, You-Ming Chang, Wei-Chen Chiu, Ning Yu
Malicious Sample Harmful Data Multimodal Datasets Content Detection Harmful Object Detection

June 28, 2024

Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
Danny Halawi, Alexander Wei, Eric Wallace, Tony T. Wang, Nika Haghtalab, Jacob Steinhardt
Fine Tuning Technical Challenge LLM Adaptation Monotone Adversary Malicious Sample Black Box Tuning

May 16, 2024

IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency
Linshan Hou, Ruili Feng, Zhongyun Hua, Wei Luo, Leo Yu Zhang, Yiming Li
Backdoor Attack Adaptive Attack Malicious Sample Input Level Backdoor Detection Parameter Oriented Scaling Consistency

March 28, 2024

MedBN: Robust Test-Time Adaptation against Malicious Test Samples
Hyejin Park, Jeongyeon Hwang, Sunung Mun, Sangdon Park, Jungseul Ok
Test Time Adaptation Batch Normalization Layer Malicious Sample

March 24, 2024

EG-ConMix: An Intrusion Detection Method based on Graph Contrastive Learning
Lijin Wu, Shanshan Lei, Feilong Liao, Yuanjun Zheng, Yuxin Liu, Wentao Fu, Hao Song, Jiajun Zhou
Internet of Thing Intrusion Detection Network Intrusion Detection Malicious Sample

March 11, 2024

Textual analysis of End User License Agreement for red-flagging potentially malicious software
Behraj Khan, Tahir Syed, Zeshan Khan, Muhammad Rafi
Text Summarization Content Analysis Malicious Sample Supervised Learning Method

January 27, 2024

Ransomware threat mitigation through network traffic analysis and machine learning techniques
Ali Mehrban, Shirin Karimi Geransayeh
New Machine Barzilai Borwein Technique Cyber Attack Network Traffic Computer Network Malicious Sample Ransomware Attack Ransomware Attack Modeling Technique

August 17, 2023

RatGPT: Turning online LLMs into Proxies for Malware Attacks
Mika Beckerich, Laura Plein, Sergio Coronado
Generative AI Cybersecurity Perspective Malware Attack Proxy Dataset State of the Art Large Malicious Sample Malicious Content

August 8, 2023

Pelta: Shielding Transformers to Mitigate Evasion Attacks in Federated Learning
Simon Queyrut, Yérom-David Bromberg, Valerio Schiavoni
Adversarial Example Transformer Megatron Decepticons Evasion Attack Malicious Sample Novel Shielding Mechanism Malicious Attack

June 9, 2023

JABBERWOCK: A Tool for WebAssembly Dataset Generation and Its Application to Malicious Website Detection
Chika Komiya, Naoto Yanai, Kyosuke Yamashita, Shingo Okamura
Application Proficiency BRIO Tool Malicious Sample WebAssembly Reverse Engineering

May 1, 2023

Classification and Online Clustering of Zero-Day Malware
Olha Jurečková, Martin Jureček, Mark Stamp, Fabio Di Troia, Róbert Lórencz
Classification Code Malware Family Online Clustering Zero Day Malicious Sample

January 29, 2023

Uncovering Adversarial Risks of Test-Time Adaptation
Tong Wu, Feiran Jia, Xiangyu Qi, Jiachen T. Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal
Test Time Adaptation Adversarial Risk Time Adaptation Malicious Sample

November 6, 2022

Going In Style: Audio Backdoors Through Stylistic Transformations
Stefanos Koffas, Luca Pajola, Stjepan Picek, Mauro Conti
Backdoor Attack Style Consistency Stylistic Change Audio Domain Malicious Sample

October 18, 2022

A Novel Feature Representation for Malware Classification
John Musgrave, Temesguen Messay-Kebede, David Kapp, Anca Ralescu
Malware Classification Malicious Sample Benign Input High Resolution Feature

August 20, 2022

Quo Vadis: Hybrid Machine Learning Meta-Model based on Contextual and Behavioral Malware Representations
Dmitrijs Trizna
Hybrid Deep Learning Hybrid Machine Learning Multiple Deep Neural Network Malware Classifier Malicious Sample Malware Representation

February 28, 2022

MaMaDroid2.0 -- The Holes of Control Flow Graphs
Harel Berger, Chen Hajaj, Enrico Mariconti, Amit Dvir
Android Malware Evasion Attack Malicious Sample Control Flow Fine Hole

February 7, 2022

Fabricated Flips: Poisoning Federated Learning without Data
Jiyue Huang, Zilong Zhao, Lydia Y. Chen, Stefanie Roos
Federated Learning Raw Data Untargeted Attack Malicious Sample Negative Flip Data Free Black Box Attack