Related papers: Plug. Play. Persist. Inside a Ready-to-Go Havoc C2…
The growing use of third-party hardware accelerators (e.g., FPGAs, ASICs) for deep neural networks (DNNs) introduces new security vulnerabilities. Conventional model-level backdoor attacks, which only poison a model's weights to misclassify…
With the rise of attacks using PowerShell in the recent months, there has not been a comprehensive solution for monitoring or prevention. Microsoft recently released the AMSI solution for PowerShell v5, however this can also be bypassed.…
Modern virtualized service infrastructures expose attack vectors that enable attacks of high severity, such as attacks targeting hypervisors. A malicious user of a guest VM (virtual machine) may execute an attack against the underlying…
We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline…
Command and control (C&C) is important in an attack. It transfers commands from the attacker to the malware in the compromised hosts. Currently, some attackers use online social networks (OSNs) in C&C tasks. There are two main problems in…
Latest ARM processors are approaching the computational power of x86 architectures while consuming much less energy. Consequently, supply follows demand with Amazon EC2, Equinix Metal and Microsoft Azure offering ARM-based instances, while…
AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a…
The hardware security community relies on databases of known vulnerabilities and open-source designs to develop formal verification methods for identifying hardware security flaws. While there are plenty of open-source designs and…
Phishing attacks remain one of the most prevalent threats to online security, with the Anti-Phishing Working Group reporting over 890,000 attacks in Q3 2025 alone. Traditional password-based authentication is particularly vulnerable to such…
We demonstrate how AI-powered cybersecurity tools can be turned against themselves through prompt injection attacks. Prompt injection is reminiscent of cross-site scripting (XSS): malicious text is hidden within seemingly trusted content,…
Virtualization promises significant benefits in security, efficiency, dependability, and cost. Achieving these benefits depends upon the reliability of the underlying virtual machine monitors (hypervisors). This paper describes an ongoing…
Hypertext transfer protocol (HTTP) is one of the most widely used protocols on the Internet. As a consequence, most attacks (i.e., SQL injection, XSS) use HTTP as the transport mechanism. Therefore, it is crucial to develop an intelligent…
Underwater datacenters (UDCs) hold promise as next-generation data storage due to their energy efficiency and environmental sustainability benefits. While the natural cooling properties of water save power, the isolated aquatic environment…
A popular run-time attack technique is to compromise the control-flow integrity of a program by modifying function return addresses on the stack. So far, shadow stacks have proven to be essential for comprehensively preventing return…
Windows operating systems (OS) are ubiquitous in enterprise Information Technology (IT) and operational technology (OT) environments. Due to their widespread adoption and known vulnerabilities, they are often the primary targets of malware…
Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences to detect such attacks. However, concealed backdoors evade…
Always-on AI agents (OpenClaw, Hermes Agent) run as a single persistent process under the owner's identity, folding messaging, memory, self-authored skills, scheduling, and shell into one authority boundary. This configuration opens what we…
Cloud computing is a convenient model for processing data remotely. However, users must trust their cloud provider with the confidentiality and integrity of the stored and processed data. To increase the protection of virtual machines, AMD…
Dynamic malware analysis requires executing untrusted binaries inside strongly isolated, rapidly resettable environments. In practice, many detonation workflows remain tied to heavyweight hypervisors or dedicated bare-metal labs, limiting…
An agentic-AI runtime issues tool calls, sends messages, and actuates devices on behalf of an LLM. Catching the four ways an action can diverge from its audit record -- F1 gate-bypass, F2 audit-forgery, silent host failure, F4 wrong-target,…