CAMLIS 2025
22 talks · 2025 · indexed by Breach Arc Archive. Links open each talk on YouTube.
Browse with filters →- A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models 2025
- Accelerating AI red teaming operations with the Python Risk Identification Tool (PyRIT) 2025
- Adaptive by Design: Contextual Reinforcement Learning for Mission-Ready Cyber Defence 2025
- Adversarial ML Attacks on Financial Reporting via Maximum Violated Multi-Objective Attack 2025
- An Agent-Based Framework for Adversarial Simulation and Blue Teaming 2025
- Attack Surfaces in Computer Use Agents: A Practical Taxonomy 2025
- BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing 2025
- Evaluating Risk-Based Authentication Effectiveness in Production 2FA Systems 2025
- Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities 2025
- Improving Accuracy and Consistency in Real-World Cybersecurity AI Systems via Test-Time Compute 2025
- Keynote - The New Geopolitics of Technology 2025
- Keynote - What Does It Mean for Agentic AI to Preserve Privacy? Mapping the New Data Sinks and Leaks 2025
- LLM Salting: From Rainbow Tables to Jailbreaks 2025
- MADAR: Efficient Continual Learning for Malware Analysis with Diversity-Aware Replay 2025
- Reason. Search. Retrieve. Repeat. Iterative Retrieval for Automating Vulnerable Code Discovery 2025
- Red Teaming AI Red Teaming 2025
- RIG-RAG: A GraphRAG Inspired Approach to Agentic Cloud Infrastructure 2025
- ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls 2025
- ShadowLogic: Hidden Backdoors in Any Whitebox LLM 2025
- Social Attack Surfaces: Emerging Cybersecurity Threats in Open Source Collaboration 2025
- Text2VLM: Adapting Text-Only Datasets to Evaluate Alignment Training in Visual Language Models 2025
- Towards a Generalisable Cyber Defence Agent for Real-World Computer Networks" 2025