Related papers: ICAN-Deploy: Identity-Stable Canary Deployment for…
Recent Pwn2Own competitions have demonstrated the continued effectiveness of control hijacking attacks despite deployed countermeasures including stack canaries and ASLR. A powerful defense called Control flow Integrity (CFI) offers a…
Auto-regressive (AR) models have recently made notable progress in image generation, achieving performance comparable to diffusion-based approaches. However, their computational intensity and sequential nature impede on-device deployment,…
The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing…
A key challenge for mobile network operators in 6G is to bring together and orchestrate a variety of new emerging players of today's mobile ecosystems in order to provide economically viable and seamless mobile connectivity in form of a…
Edge AI is often framed as model compression and deployment under tight constraints. We argue a stronger operational thesis: Edge AI in realistic deployments is necessarily adaptive. In long-horizon operation, a fixed (non-adaptive)…
Trust-building mechanisms among network entities of different administrative domains will gain significant importance in 6G because a future mobile network will be operated cooperatively by a variety of different stakeholders rather than by…
We present Labeled Input Output in F* (LIO*), a verified framework that enforces information flow control (IFC) policies developed in F* and automatically extracted to C. Inspired by LIO, we encapsulated IFC policies into effects, but using…
By sharing local sensor information via Vehicle-to-Vehicle (V2V) wireless communication networks, Cooperative Adaptive Cruise Control (CACC) is a technology that enables Connected and Automated Vehicles (CAVs) to drive autonomously on the…
Increasing automation in vehicles enabled by increased connectivity to the outside world has exposed vulnerabilities in previously siloed automotive networks like controller area networks (CAN). Attributes of CAN such as broadcast-based…
Integrating an automated driving software stack into vehicles with variable configuration is challenging, especially due to different hardware characteristics. Further, to provide software updates to a vehicle fleet in the field, the…
In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection. We find that the stumbling block to their generalization is caused by the unexpected learned identity representation on images.…
We present Canary, a scheduling architecture that allows high performance analytics workloads to scale out to run on thousands of cores. Canary is motivated by the observation that a central scheduler is a bottleneck for high performance…
Binary program vulnerability detection is critical for software security, yet existing deep learning approaches often rely on source code analysis, limiting their ability to detect unknown vulnerabilities. To address this, we propose…
Reliable and secure communication is essential for mission-critical aerospace and defence operations involving autonomous platforms such as Unmanned Aerial Vehicles (UAVs), satellites, and ground control systems. In contested or dynamic…
Property-Directed Reachability (PDR/IC3) is a standard workhorse for hardware safety verification, but most implementations are tuned primarily for time-to-answer and treat the produced invariant or counterexample as a secondary byproduct.…
The emerging Internet of AI Agents challenges existing web infrastructure designed for human-scale, reactive interactions. Unlike traditional web resources, autonomous AI agents initiate actions, maintain persistent state, spawn sub-agents,…
Large language models deployed at runtime can misbehave in ways that clean-data validation cannot anticipate: training-time backdoors lie dormant until triggered, jailbreaks subvert safety alignment, and prompt injections override the…
AI-powered edge computing security is moving Intelligent Transportation Systems (ITS) from passive, rule-based protections to proactive, smart, zero-touch, self-sufficient safeguards that neutralize threats in milliseconds. As…
Many research papers have recently focused on behavioral-based driver authentication systems in vehicles. Pushed by Artificial Intelligence (AI) advancements, these works propose powerful models to identify drivers through their unique…
Policy Cards are introduced as a machine-readable, deployment-layer standard for expressing operational, regulatory, and ethical constraints for AI agents. The Policy Card sits with the agent and enables it to follow required constraints at…