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

BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing

NIEBEZPIECZNE ZWIĄZKI byłego PEŁNOMOCNIKA RZĄDU TUSKA. Kontrwywiad musiał zadziałać

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

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

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

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

AGAPI: AtomGPT.org API for Agentic AI in Materials Discovery and Design

Attack Surfaces in Computer Use Agents: A Practical Taxonomy

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

Всего 40 строк кода

Evaluating Risk-Based Authentication Effectiveness in Production 2FA Systems

ShadowLogic: Hidden Backdoors in Any Whitebox LLM

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

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

LLM Salting: From Rainbow Tables to Jailbreaks

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

Social Attack Surfaces: Emerging Cybersecurity Threats in Open Source Collaboration

OpenClaw: чит-код для продуктивности или подарок хакерам?

За что мы на самом деле ненавидим HR

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