CAMLIS 2024
Conference on Applied Machine Learning in Information Security 2024

Table of Contents

• Defending Large Language Models Against Attacks With Residual Stream Activation Analysis 1-15
  Amelia Kawasaki , Andrew Davis , Houssam Abbas
• Curl: Private LLMs through Wavelet-Encoded Look-Up Tables 16-47
  Manuel B. Santos , Dimitris Mouris , Mehmet Ugurbil , Stanislaw Jarecki , José Reis , Shubho Sengupta , Miguel de Vega
• Defending Against Indirect Prompt Injection Attacks With Spotlighting 48-62
  Keegan Hines , Gary Lopez , Matthew Hall , Federico Zarfati , Yonatan Zunger , Emre Kıcıman
• Towards autonomous cyber-defence: using co-operative decision making for cybersecurity 63-82
  Madeline Cheah , Jack Stone , Samuel Bailey , Peter Haubrick , David Rimmer , Matt Lacey , Mark Dorn
• PEVuln: A Benchmark Dataset for Using Machine Learning to Detect Vulnerabilities in PE Malware 83-113
  Nathan Ross , Oluwafemi Olukoya , Jesús Martínez del Rincón , Domhnall Carlin
• Applying Action Masking and Curriculum Learning Techniques to Improve Data Efficiency and Overall Performance in Operational Technology Cyber Security using Reinforcement Learning 114-128
  Alec Wilson , William Holmes , Ryan Menzies , Kez Smithson Whitehead
• Navigating Concept Drift and Packing Complexity in Malware Family Classification 129-144
  Numan Halit Guldemir , Oluwafemi Olukoya , Jesús Martínez-del-Rincón
• DIP-ECOD: Improving Anomaly Detection in Multimodal Distributions 145-160
  Kaixi Yang , Paul Miller , Jesús Martinez-del-Rincon
• LLM agents for vulnerability identification and verification of CVEs 161-173
  Tadesse ZeMicheal , Hsin Chen , Shawn Davis , Rachel Allen , Michael Demoret , Ashley Song
• Ransomware Evolution: Unveiling Patterns Using HDBSCAN 174-189
  Prajna Bhandary , Robert J. Joyce , Charles Nicholas
• Is 𝐹1 Score Suboptimal for Cybersecurity Models? Introducing 𝐶𝑠𝑐𝑜𝑟𝑒, a Cost-Aware Alternative for Model Assessment 190-209
  Manish Marwah , Asad Narayanan , Stephan Jou , Martin Arlitt , Maria Pospelova
• AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees 210-223
  William Fleshman , Benjamin Van Durme
• PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI Systems 224-241
  Gary D. Lopez Munoz , Amanda J. Minnich , Roman Lutz , Richard Lundeen , Raja Sekhar Rao Dheekonda , Nina Chikanov , Bolor-Erdene Jagdagdorj , Martin Pouliot , Shiven Chawla , Whitney Maxwell , Blake Bullwinkel , Katherine Pratt , Joris de Gruyter , Charlotte Siska , Pete Bryan , Tori Westerhoff , Chang Kawaguchi , Christian Seifert , Ram Shankar Siva Kumar , Yonatan Zunger
• Binary Malware Attribution using LLM Embeddings and Topological Data Analysis 242-256
  Kincaid MacDonald , Ajai Ruparelia , Boomer Rogers , Adonis Bovell , Branden Stone
• Embedding-based classifiers can detect prompt injection attacks 257-268
  Md. Ahsan Ayub , Subhabrata Majumdar