Adversarial Machine Learning Attacks on Financial Reporting via Maximum Violated Multi-Objective Attack

Edward Raff, Karen Kukla, Michel Benaroch, Joseph Comprix; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:1-27

[abs][Download PDF]

Text2VLM: Adapting Text-Only Datasets to Evaluate Alignment Training in Visual Language Models

Gabriel Downer, Sean Craven, Damian Ruck, Jake Thomas; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:28-41

[abs][Download PDF][Software][Supplementary PDF]

Democratizing ML for Enterprise Security: A Self-Sustained Attack Detection Framework

Sadegh Momeni, Ge Zhang, Birkett Huber, Hamza Harkous, Sam Lipton, Benoit Seguin, Yanis Pavlidis; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:42-65

[abs][Download PDF][Supplementary PDF]

Red Teaming AI Red Teaming

Subhabrata Majumdar, Brian Pendleton, Abhishek Gupta; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:66-86

[abs][Download PDF]

Towards a Generalisable Cyber Defence Agent for Real-World Computer Networks

Tim Dudman, Martyn Bull; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:87-109

[abs][Download PDF]

Causal Reinforcement Learning for Labelling Optimization in Cyber Anomaly Detection

Susan Babirye, Gong Yu, Shimadzu Hideyasu, Kyriakopoulos Konstantinos; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:110-134

[abs][Download PDF]

PD-AutoR: Towards Automatic Restoration of Poisoned Examples in Machine Learning

Haoyang Chen, Xinyun Liu, Xu Zhou, Ziao Jiao, Xinyu Lei; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:135-167

[abs][Download PDF]

ShadowLogic: Backdoors in Any Whitebox LLM

Kasimir Schulz, Amelia Kawasaki, Leo Ring; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:168-179

[abs][Download PDF]

ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls

Sanket Badhe; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:180-199

[abs][Download PDF]

A Framework for Rapidly Developing and Deploying Protection Against Large Language Model Attacks

Adam Swanda, Amy Chang, Alexander Chen, Fraser Burch, Paul Kassianik, Konstantin Berlin; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:200-221

[abs][Download PDF]

Evaluating LLM Generated Detection Rules in Cybersecurity

Anna Bertiger, Bobby Filar, Aryan Luthra, Stefano Meschiari, Aiden Mitchell, Sam Scholten, Vivek Sharath; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:222-238

[abs][Download PDF]

RoleSentry: A Multi-Stage Framework for Explainable Detection of AWS Role Chaining Attacks

Godwin Attigah, Austin Gansz; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:239-264

[abs][Download PDF]

MADAR: Efficient Continual Learning for Malware Analysis with Distribution-Aware Replay

Mohammad Saidur Rahman, Scott Coull, Qi Yu, Matthew Wright; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:265-291

[abs][Download PDF]

RIG-RAG: A GraphRAG Inspired Approach to Agentic Cloud Infrastructure

Benji Lilley, Brian Mitchell, Spiros Mancoridis; Proceedings of the 2025 Conference on Applied Machine Learning for Information Security, PMLR 299:292-311

[abs][Download PDF]