2025 Presentations

DAY-1

[Keynote] Niloofar Mireshghallah: What Does It Mean for Agentic AI to Preserve Privacy? Mapping the New Data Sinks and Leaks

Javad Rafiei Asl: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models

Tamás Vörös: LLM Salting: From Rainbow Tables to Jailbreaks

Amelia Kawasaki: ShadowLogic: Hidden Backdoors in Any Whitebox LLM

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

Tim Dudman: Towards a Generalisable Cyber Defence Agent for Real-World Computer Networks"

Ashley Song: Improving Accuracy and Consistency in Real-World Cybersecurity AI Systems via Test-Time Compute

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

DAY-2

[Keynote] Nathaniel Fick: Keynote - The New Geopolitics of Technology

Jake Thomas: Adaptive by Design: Contextual Reinforcement Learning for Mission-Ready Cyber Defense

Mohammad Saidur Rahman: MADAR: Efficient Continual Learning for Malware Analysis with Diversity-Aware Replay

Supriti Vijay: Reason. Search. Retrieve. Repeat. Iterative Retrieval for Automating Vulnerable Code Discovery

Christopher Honaker: Social Attack Surfaces: Emerging Cybersecurity Threats in Open Source Collaboration

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

Steven Leung: Evaluating Risk-Based Authentication Effectiveness in Production 2FA Systems

[Posters Session] Click here to view all posters

CAMLIS RED

Daniel Jones: Attack Surfaces in Computer Use Agents: A Practical Taxonomy

Nina Chikanov: Accelerating AI red teaming operations with the Python Risk Identification Tool (PyRIT)

Caelin Kaplan: BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing

Gary Lopez Munoz: An Agent-Based Framework for Adversarial Simulation and Blue Teaming

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

Arjun Krishna: Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities

Subhabrata Majumdar: Red Teaming AI Red Teaming