Related papers: OAMAC: Origin-Aware Mandatory Access Control for P…
Oblivious RAM (ORAM) is a cryptographic primitive which obfuscates the access patterns to a storage thereby preventing privacy leakage. So far in the current literature, only `fully functional' ORAMs are widely studied which can protect, at…
LLM-powered agents often use prompt compression to reduce inference costs, but this introduces a new security risk. Compression modules, which are optimized for efficiency rather than safety, can be manipulated by adversarial inputs,…
Algorithms for oblivious random access machine (ORAM) simulation allow a client, Alice, to obfuscate a pattern of data accesses with a server, Bob, who is maintaining Alice's outsourced data while trying to learn information about her data.…
Code reuse attacks are still big threats to software and system security. Control flow integrity is a promising technique to defend against such attacks. However, its effectiveness has been weakened due to the inaccurate control flow graph…
The Model Context Protocol (MCP) replaces static, developer-controlled API integrations with more dynamic, user-driven agent systems, which also introduces new security risks. As MCP adoption grows across community servers and major…
Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…
Recent proliferation of embedded systems has generated a bold new paradigm, known as open embedded systems. While traditional embedded systems provide only closed base applications (natively-installed software) to users, open embedded…
The hardware/software boundary in modern heterogeneous multicore computers is increasingly complex, and diverse across different platforms. A single memory access by a core or DMA engine traverses multiple hardware translation and caching…
We introduce IMPACT, a set of high-throughput main memory-based timing attacks that leverage characteristics of processing-in-memory (PiM) architectures to establish covert and side channels. IMPACT enables high-throughput communication and…
Modern computing platforms rely on the Unified Extensible Firmware Interface (UEFI) to initialize hardware and coordinate the transition to the operating system. Because this execution environment operates with high privileges and persists…
Permissions are highly sensitive in Internet-of-Things (IoT) applications, as IoT devices collect our personal data and control the safety of our environment. Rather than simply granting permissions, further constraints shall be imposed on…
In recent years, cloud storage technology has been widely used in many fields such as education, business, medical and more because of its convenience and low cost. With the widespread applications of cloud storage technology, data access…
The Model Context Protocol (MCP) has emerged as the de facto standard for connecting Large Language Models (LLMs) to external data and tools, effectively functioning as the "USB-C for Agentic AI." While this decoupling of context and…
Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…
AI agents increasingly require direct, structured access to application data and actions, but production deployments still struggle to express and verify the governance properties that matter in practice: least-privilege authorization,…
Recent attacks have broken process isolation by exploiting microarchitectural side channels that allow indirect access to shared microarchitectural state. Enclaves strengthen the process abstraction to restore isolation guarantees. We…
We present a shared control paradigm that improves a user's ability to operate complex, dynamic systems in potentially dangerous environments without a priori knowledge of the user's objective. In this paradigm, the role of the autonomous…
Process querying is used to extract information and insights from process execution data. Similarly, process constraints can be checked against input data, yielding information on which process instances violate them. Traditionally, such…
Transactional memory allows the user to declare sequences of instructions as speculative \emph{transactions} that can either \emph{commit} or \emph{abort}. If a transaction commits, it appears to be executed sequentially, so that the…
Distributed data analytics platforms (i.e., Apache Spark, Hadoop) provide high-level APIs to programmatically write analytics tasks that are run distributedly in multiple computing nodes. The design of these frameworks was primarily…