CAMLIS

Red Teaming AI Red Teaming

CAMLIS

Importing Phantoms Measuring LLM Package Hallucination Vulnerabilities

CAMLIS

BlackIce A Containerized Red Teaming Toolkit for AI Security Testing

CAMLIS

An Agent-Based Framework for Adversarial Simulation and Blue Teaming

CAMLIS

ScamAgents How AI Agents Can Simulate Human-Level Scam Calls

CAMLIS

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

CAMLIS

Attack Surfaces in Computer Use Agents A Practical Taxonomy

CAMLIS

Evaluating Risk-Based Authentication Effectiveness in Production 2FA Systems

CAMLIS

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

CAMLIS

Social Attack Surfaces Emerging Cybersecurity Threats in Open Source Collaboration

CAMLIS

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

CAMLIS

MADAR Efficient Continual Learning for Malware Analysis with Diversity-Aware Replay

CAMLIS

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

CAMLIS

RIG-RAG A GraphRAG Inspired Approach to Agentic Cloud Infrastructure

CAMLIS

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

CAMLIS

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

CAMLIS

Adaptive by Design Contextual Reinforcement Learning for Mission-Ready Cyber Defence

CAMLIS

LLM Salting From Rainbow Tables to Jailbreaks

CAMLIS

ShadowLogic Hidden Backdoors in Any Whitebox LLM

CAMLIS

A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models

CAMLIS

Keynote - The New Geopolitics of Technology

CAMLIS

Keynote - What Does It Mean for Agentic AI to Preserve Privacy Mapping the New Data Sinks and Leaks

CAMLIS

Keynote Panel

CAMLIS

AdapterSwap Continuous Training of LLMs with Data Removal and Access-Control Guarantees

CAMLIS

Defending Large Language Models Against Attacks With Residual Stream Activation Analysis

CAMLIS

LLM Backdoor Activations Stick Together

CAMLIS

Curl Private LLMs through Wavelet-Encoded Look-Up Tables

CAMLIS

Hamm-Grams Mining Common Regular Expressions via Locality Sensitive Hashing

CAMLIS

Let’s Make it Personal Customizing Threat Intelligence with Metric Learning

CAMLIS

Defending Against Indirect Prompt Injection Attacks With Spotlighting

CAMLIS