Related papers: Sandlock: Confining AI Agent Code with Unprivilege…
Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…
In this work we present the Secure Machine, SeM for short, a CPU architecture extension for secure computing. SeM uses a small amount of in-chip additional hardware that monitors key communication channels inside the CPU chip, and only acts…
Range locks are a synchronization construct designed to provide concurrent access to multiple threads (or processes) to disjoint parts of a shared resource. Originally conceived in the file system context, range locks are gaining increasing…
Trusted execution environments (TEEs) provide an environment for running workloads in the cloud without having to trust cloud service providers, by offering additional hardware-assisted security guarantees. However, main memory encryption…
Modern Security Operations Centers struggle with alert fatigue, fragmented tooling, and limited cross-source event correlation. Challenges that current Security Information Event Management and Extended Detection and Response systems only…
Prior studies on deception in language-based AI agents typically assess whether the agent produces a false statement about a topic, or makes a binary choice prompted by a goal, rather than allowing open-ended deceptive behavior to emerge in…
Modern processors can offer hardware primitives that allow a process to run in isolation. These primitives implement a trusted execution environment (TEE) in which a program can run such that the integrity and confidentiality of its…
Agentic AI systems can plan, call tools, inspect code, interact with web applications, and coordinate multi-step workflows. These same capabilities change the economics of cyber offense. The central near-term risk is not that every…
The software supply chain attacks are becoming more and more focused on trusted development and delivery procedures, so the conventional post-build integrity mechanisms cannot be used anymore. The available frameworks like SLSA, SBOM and in…
Agentic AI systems automate enterprise workflows but existing defenses--guardrails, semantic filters--are probabilistic and routinely bypassed. We introduce authenticated workflows, the first complete trust layer for enterprise agentic AI.…
Modern applications are increasingly advanced and complex, and inevitably contain exploitable software bugs despite the ongoing efforts. The applications today often involve processing of sensitive information. However, the lack of…
Operating Systems enforce logical isolation using abstractions such as processes, containers, and isolation technologies to protect a system from malicious or buggy code. In this paper, we show new types of side channels through the file…
As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees…
This paper introduces BioAgent Bench, a benchmark dataset and an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks. The benchmark contains curated end-to-end tasks (e.g.,…
Software is everywhere. The increasing requirement of supporting a wide variety of domains has rapidly increased the complexity of software systems, making them hard to maintain and the training process harder for end-users, which in turn…
Security Enhanced Linux (SELinux) is a security architecture for Linux implementing mandatory access control. It has been used in numerous security-critical contexts ranging from servers to mobile devices. But this is challenging as SELinux…
LLM-based agents are increasingly deployed to autonomously solve complex tasks, raising urgent needs for IP protection and regulatory provenance. While content watermarking effectively attributes LLM-generated outputs, it fails to directly…
In-storage computing with modern solid-state drives (SSDs) enables developers to offload programs from the host to the SSD. It has been proven to be an effective approach to alleviating the I/O bottleneck. To facilitate in-storage…
As the automotive industry transitions toward centralized Linux-based architectures, ensuring the predictable execution of mixed-criticality applications becomes essential. However, concurrent use of the Linux network stack introduces…
Multicore processors constitute the main architecture choice for modern computing systems in different market segments. Despite their benefits, the contention that naturally appears when multiple applications compete for the use of shared…