DeepStage: Learning Autonomous Defense Policies against Multi-Stage APT Campaigns

This paper presents DeepStage, a deep reinforcement learning DRL framework for adaptive, stage-aware defense against Advanced Persistent Threats APTs. The enterprise environment is modeled as a partially observable Markov decision process POMDP, where host provenance and network telemetry are fus...

A one-prompt attack that breaks LLM safety alignment

Large language models LLMs and diffusion models now power a wide range of applications, from document assistance to text-to-image generation, and users increasingly expect these systems to be safety-aligned by default. Yet safety alignment is only as robust as its weakest failure mode. Despite...

Topology Generation of UAV Covert Communication Networks: a Graph Diffusion Approach with Incentive Mechanism

With the growing demand for Uncrewed Aerial Vehicle UAV networks in sensitive applications, such as urban monitoring, emergency response, and secure sensing, ensuring reliable connectivity and covert communication has become increasingly vital. However, dynamic mobility and exposure risks pose...

DMRL: Data- and Model-Aware Reward Learning for Data Extraction

Large language models LLMs are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from several limitations: 1 rely on dataset duplicates...

Avoiding Death by a Thousand Scripts: Using Automated Content Security Policies

Businesses know they need to secure their client-side scripts. Content security policies CSPs are a great way to do that. But CSPs are cumbersome. One mistake and you have a potentially significant client-side security gap. Finding those gaps means long and tedious hours or days in manual code...