CAMLIS 2024

Table of Contents

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